LRP-DS: Lightweight RepPoints with Decoupled Sampling Point Set

Most object detection methods use rectangular bounding boxes to represent the object, while the representative points network (RepPoints) employs a point set to describe the object. The RepPoints can provide more fine-grained localization and facilitates classification. However, it ignores the difference between localization and classification tasks. Therefore, a lightweight RepPoints with decoupling of the sampling point set (LRP-DS) is proposed in this paper. Firstly, the lightweight MobileNet-V2 and Feature Pyramid Networks (FPN) is employed as the backbone network to realize the lightweight network, rather than the Resnet. Secondly, considering the difference between classification and localization tasks, the sampling points of classification and localization are decoupled, by introducing classification free sampling method. Finally, due to the introduction of the classification free sampling method, the problem of the mismatch between the localization accuracy and the classification confidence is highlighted, so the localization score is employed to describe the localization accuracy independently. The final network structure of this paper achieves 73.3% mean average precision (mAP) on the VOC07 test dataset, which is 1.9% higher than original RepPoints with the same backbone network MobileNetV2 and FPN. Our LRP-DS has a detection speed of 20FPS for the input image of (1000, 600), on RTX2060 GPU, which is nearly twice as fast as the backbone network of ResNet50 and FPN. Experimental results show the effectiveness of our method.

Download Full-text

A generalised approach for high-throughput instance segmentation of stomata in microscope images

Plant Methods ◽

10.1186/s13007-021-00727-4 ◽

2021 ◽

Vol 17 (1) ◽

Author(s):

Hiranya Jayakody ◽

Paul Petrie ◽

Hugo Jan de Boer ◽

Mark Whitty

Keyword(s):

High Throughput ◽

Imaging Techniques ◽

Detection Algorithm ◽

Input Image ◽

Detection Methods ◽

Sample Collection ◽

High Throughput Analysis ◽

General Applicability ◽

Additional Image ◽

Bounding Boxes

Abstract Background Stomata analysis using microscope imagery provides important insight into plant physiology, health and the surrounding environmental conditions. Plant scientists are now able to conduct automated high-throughput analysis of stomata in microscope data, however, existing detection methods are sensitive to the appearance of stomata in the training images, thereby limiting general applicability. In addition, existing methods only generate bounding-boxes around detected stomata, which require users to implement additional image processing steps to study stomata morphology. In this paper, we develop a fully automated, robust stomata detection algorithm which can also identify individual stomata boundaries regardless of the plant species, sample collection method, imaging technique and magnification level. Results The proposed solution consists of three stages. First, the input image is pre-processed to remove any colour space biases occurring from different sample collection and imaging techniques. Then, a Mask R-CNN is applied to estimate individual stomata boundaries. The feature pyramid network embedded in the Mask R-CNN is utilised to identify stomata at different scales. Finally, a statistical filter is implemented at the Mask R-CNN output to reduce the number of false positive generated by the network. The algorithm was tested using 16 datasets from 12 sources, containing over 60,000 stomata. For the first time in this domain, the proposed solution was tested against 7 microscope datasets never seen by the algorithm to show the generalisability of the solution. Results indicated that the proposed approach can detect stomata with a precision, recall, and F-score of 95.10%, 83.34%, and 88.61%, respectively. A separate test conducted by comparing estimated stomata boundary values with manually measured data showed that the proposed method has an IoU score of 0.70; a 7% improvement over the bounding-box approach. Conclusions The proposed method shows robust performance across multiple microscope image datasets of different quality and scale. This generalised stomata detection algorithm allows plant scientists to conduct stomata analysis whilst eliminating the need to re-label and re-train for each new dataset. The open-source code shared with this project can be directly deployed in Google Colab or any other Tensorflow environment.

Download Full-text

A Generalised Approach for High-throughput Instance Segmentation of Stomata in Microscope Images

10.21203/rs.3.rs-33223/v1 ◽

2020 ◽

Author(s):

Hiranya Samanga Jayakody ◽

Paul Petrie ◽

Hugo de Boer ◽

Mark Whitty

Keyword(s):

High Throughput ◽

Imaging Techniques ◽

Detection Algorithm ◽

Input Image ◽

Detection Methods ◽

Sample Collection ◽

High Throughput Analysis ◽

General Applicability ◽

Additional Image ◽

Bounding Boxes

Abstract Background: Stomata analysis using microscope imagery provides important insight into plant physiology, health and the surrounding environmental conditions. Plant scientists are now able to conduct automated high-throughput analysis of stomata in microscope data, however, existing detection methods are sensitive to the appearance of stomata in the training images, thereby limiting general applicability. In addition, existing methods only generate bounding-boxes around detected stomata, which require users to implement additional image processing steps to study stomata morphology. In this paper, we develop a fully automated, robust stomata detection algorithm which can also identify individual stomata boundaries regardless of the plant species, sample collection method, imaging technique and magnification level. Results: The proposed solution consists of three stages. Firstly, the input image is pre-processed to remove any colour-space biases occurring from different sample collection and imaging techniques. Secondly, a Mask R-CNN is applied to estimate individual stomata boundaries and the feature pyramid network embedded in the Mask R-CNN allows the network to identify stomata at different scales. Finally, a statistical filter is implemented at the Mask R-CNN output to reduce the number of false positive generated by the network. The algorithm was tested using 16 datasets from 12 sources, containing over 60,000 stomata. For the first time in this domain, the proposed solution was tested against 7 microscope datasets never seen by the algorithm to show the generalisability of the solution. Results indicated that the proposed approach can detect stomata with a precision, recall, and F-score of 95.10%, 83.34%, and 88.61%, respectively. A separate test conducted by comparing estimated stomata boundary values with manually measured data showed that the proposed method has an IoU score of 0.70; a 7% improvement over the bounding-box approach. Conclusion: The proposed method shows robust performance across multiple microscope image datasets of different quality and scale. This generalised stomata detection algorithm allows plant scientists to conduct stomata analysis whilst eliminating the need to re-label and re-train for each new dataset. The open-source code for the project can be directly deployed in Google Colab or any other Tensorflow environment.

Download Full-text

R-YOLO: A Real-Time Text Detector for Natural Scenes with Arbitrary Rotation

Sensors ◽

10.3390/s21030888 ◽

2021 ◽

Vol 21 (3) ◽

pp. 888

Author(s):

Xiqi Wang ◽

Shunyi Zheng ◽

Ce Zhang ◽

Rui Li ◽

Li Gui

Keyword(s):

Real Time ◽

Detection Efficiency ◽

Input Image ◽

Text Detection ◽

Detection Methods ◽

Natural Image ◽

Natural Scenes ◽

Novel Method ◽

Bounding Boxes ◽

Image Streams

Accurate and efficient text detection in natural scenes is a fundamental yet challenging task in computer vision, especially when dealing with arbitrarily-oriented texts. Most contemporary text detection methods are designed to identify horizontal or approximately horizontal text, which cannot satisfy practical detection requirements for various real-world images such as image streams or videos. To address this lacuna, we propose a novel method called Rotational You Only Look Once (R-YOLO), a robust real-time convolutional neural network (CNN) model to detect arbitrarily-oriented texts in natural image scenes. First, a rotated anchor box with angle information is used as the text bounding box over various orientations. Second, features of various scales are extracted from the input image to determine the probability, confidence, and inclined bounding boxes of the text. Finally, Rotational Distance Intersection over Union Non-Maximum Suppression is used to eliminate redundancy and acquire detection results with the highest accuracy. Experiments on benchmark comparison are conducted upon four popular datasets, i.e., ICDAR2015, ICDAR2013, MSRA-TD500, and ICDAR2017-MLT. The results indicate that the proposed R-YOLO method significantly outperforms state-of-the-art methods in terms of detection efficiency while maintaining high accuracy; for example, the proposed R-YOLO method achieves an F-measure of 82.3% at 62.5 fps with 720 p resolution on the ICDAR2015 dataset.

Download Full-text

A Generalised Approach for High-throughput Instance Segmentation of Stomata in Microscope Images

10.21203/rs.3.rs-33223/v3 ◽

2020 ◽

Author(s):

Hiranya Samanga Jayakody ◽

Paul Petrie ◽

Hugo de Boer ◽

Mark Whitty

Keyword(s):

High Throughput ◽

Imaging Techniques ◽

Detection Algorithm ◽

Input Image ◽

Detection Methods ◽

Sample Collection ◽

High Throughput Analysis ◽

General Applicability ◽

Additional Image ◽

Bounding Boxes

Abstract Background: Stomata analysis using microscope imagery provides important insight into plant physiology, health and the surrounding environmental conditions. Plant scientists are now able to conduct automated high-throughput analysis of stomata in microscope data, however, existing detection methods are sensitive to the appearance of stomata in the training images, thereby limiting general applicability. In addition, existing methods only generate bounding-boxes around detected stomata, which require users to implement additional image processing steps to study stomata morphology. In this paper, we develop a fully automated, robust stomata detection algorithm which can also identify individual stomata boundaries regardless of the plant species, sample collection method, imaging technique and magnification level. Results: The proposed solution consists of three stages. First, the input image is pre-processed to remove any colour space biases occurring from different sample collection and imaging techniques. Then, a Mask R-CNN is applied to estimate individual stomata boundaries. The feature pyramid network embedded in the Mask R-CNN is utilised to identify stomata at different scales. Finally, a statistical filter is implemented at the Mask R-CNN output to reduce the number of false positive generated by the network. The algorithm was tested using 16 datasets from 12 sources, containing over 60,000 stomata. For the first time in this domain, the proposed solution was tested against 7 microscope datasets never seen by the algorithm to show the generalisability of the solution. Results indicated that the proposed approach can detect stomata with a precision, recall, and F-score of 95.10\%, 83.34\%, and 88.61\%, respectively. A separate test conducted by comparing estimated stomata boundary values with manually measured data showed that the proposed method has an IoU score of 0.70; a 7\% improvement over the bounding-box approach. Conclusions: The proposed method shows robust performance across multiple microscope image datasets of different quality and scale. This generalised stomata detection algorithm allows plant scientists to conduct stomata analysis whilst eliminating the need to re-label and re-train for each new dataset. The open-source code shared with this project can be directly deployed in Google Colab or any other Tensorflow environment.

Download Full-text

A Generalised Approach for High-throughput Instance Segmentation of Stomata in Microscope Images

10.21203/rs.3.rs-33223/v2 ◽

2020 ◽

Author(s):

Hiranya Samanga Jayakody ◽

Paul Petrie ◽

Hugo de Boer ◽

Mark Whitty

Keyword(s):

High Throughput ◽

Imaging Techniques ◽

Detection Algorithm ◽

Input Image ◽

Detection Methods ◽

Sample Collection ◽

High Throughput Analysis ◽

General Applicability ◽

Additional Image ◽

Bounding Boxes

Abstract Background: Stomata analysis using microscope imagery provides important insight into plant physiology, health and the surrounding environmental conditions. Plant scientists are now able to conduct automated high-throughput analysis of stomata in microscope data, however, existing detection methods are sensitive to the appearance of stomata in the training images, thereby limiting general applicability. In addition, existing methods only generate bounding-boxes around detected stomata, which require users to implement additional image processing steps to study stomata morphology. In this paper, we develop a fully automated, robust stomata detection algorithm which can also identify individualstomata boundaries regardless of the plant species, sample collection method, imaging technique and magnfication level.Results: The proposed solution consists of three stages. First, the input image is pre-processed to remove any colour space biases occurring from different sample collection and imaging techniques. Then, a Mask R-CNN is applied to estimate individual stomata boundaries. The feature pyramid network embedded in the Mask R-CNN is utilised to identify stomata at different scales. Finally, a statistical lter is implemented at the Mask R-CNN output to reduce the number of false positive generated by the network.The algorithm was tested using 16 datasets from 12 sources, containing over 60,000 stomata. For the rst time in this domain, the proposed solution was tested against 7 microscope datasets never seen by the algorithm to show the generalisability of the solution. Results indicated that the proposed approach can detect stomata with a precision, recall, and F-score of 95.10%, 83.34%, and 88.61%, respectively. A separate test conducted by comparing estimated stomata boundary values with manually measured data showed that the proposed method has an IoU score of 0.70; a 7% improvement over the bounding-box approach.Conclusions: The proposed method shows robust performance across multiple microscope image datasets of different quality and scale. This generalised stomata detection algorithm allows plant scientists to conduct stomata analysis whilst eliminating the need to re-label and re-train for each new dataset. The open-source code shared with this project can be directly deployed in Google Colab or any other Tensorflow environment.

Download Full-text

A Stochastic Model for Block Segmentation of Images Based on the Quadtree and the Bayes Code for It

Entropy ◽

10.3390/e23080991 ◽

2021 ◽

Vol 23 (8) ◽

pp. 991

Author(s):

Yuta Nakahara ◽

Toshiyasu Matsushima

Keyword(s):

Computational Cost ◽

Block Size ◽

Input Image ◽

Generative Model ◽

Image Size ◽

Variable Block ◽

General Data ◽

The Difference ◽

Segmentation Of Images ◽

Target Data

In information theory, lossless compression of general data is based on an explicit assumption of a stochastic generative model on target data. However, in lossless image compression, researchers have mainly focused on the coding procedure that outputs the coded sequence from the input image, and the assumption of the stochastic generative model is implicit. In these studies, there is a difficulty in discussing the difference between the expected code length and the entropy of the stochastic generative model. We solve this difficulty for a class of images, in which they have non-stationarity among segments. In this paper, we propose a novel stochastic generative model of images by redefining the implicit stochastic generative model in a previous coding procedure. Our model is based on the quadtree so that it effectively represents the variable block size segmentation of images. Then, we construct the Bayes code optimal for the proposed stochastic generative model. It requires the summation of all possible quadtrees weighted by their posterior. In general, its computational cost increases exponentially for the image size. However, we introduce an efficient algorithm to calculate it in the polynomial order of the image size without loss of optimality. As a result, the derived algorithm has a better average coding rate than that of JBIG.

Download Full-text

Elimination of outlier measurements for damage detection of structures under changing environmental conditions

Structural Health Monitoring ◽

10.1177/1475921721998476 ◽

2021 ◽

pp. 147592172199847

Author(s):

William Soo Lon Wah ◽

Yining Xia

Keyword(s):

Damage Detection ◽

Multiple Regression ◽

Natural Frequencies ◽

Detection Method ◽

Detection Methods ◽

Structure Model ◽

Bridge Structure ◽

Beam Structure ◽

Dependent Variables ◽

The Difference

Damage detection methods developed in the literature are affected by the presence of outlier measurements. These measurements can prevent small levels of damage to be detected. Therefore, a method to eliminate the effects of outlier measurements is proposed in this article. The method uses the difference in fits to examine how deleting an observation affects the predicted value of a model. This allows the observations that have a large influence on the model created, to be identified. These observations are the outlier measurements and they are eliminated from the database before the application of damage detection methods. Eliminating the outliers before the application of damage detection methods allows the normal procedures to detect damage, to be implemented. A multiple-regression-based damage detection method, which uses the natural frequencies as both the independent and dependent variables, is also developed in this article. A beam structure model and an experimental wooden bridge structure are analysed using the multiple-regression-based damage detection method with and without the application of the method proposed to eliminate the effects of outliers. The results obtained demonstrate that smaller levels of damage can be detected when the effects of outlier measurements are eliminated using the method proposed in this article.

Download Full-text

Integrative Leadership is a Precursor of Engagement of Bank Employees in Pakistan

International Journal of Human Resource Studies ◽

10.5296/ijhrs.v7i3.11673 ◽

2017 ◽

Vol 7 (3) ◽

pp. 257

Author(s):

Sanober Salman Shaikh ◽

Chiraprapha Akaraborworn

Keyword(s):

Employee Engagement ◽

Quantitative Research ◽

Sampling Method ◽

Final Analysis ◽

Foreign Banks ◽

Private Banks ◽

Bank Employees ◽

The Difference ◽

Integrative Leadership ◽

The Relationship

The purpose of this study was twofold: to examine the relationship and determine the predictive power of integrative leadership on employee engagement. To achieve the mentioned objectives, the quantitative research method was employed and data was collected through survey questionnaire from 1000 operational employees of all 21 private banks in Pakistan. The sample of 819 respondents was utilized for final analysis. Two stage sampling method was performed; non- probability sampling and stratified random sampling. The data analysis was done by use of correlation and multiple regression. The result indicated a positive correlation among all of the nine constructs of integrative leadership with employee engagement and the six constructs of integrative leadership significantly predicted employees’ engagement in private banks in Pakistan. Additionally, analysis of variance was performed to assess the differences in employee engagement among the respondents’ demographic characteristics. The ANOVA result showed that the employees working in a conventional and Islamic bank and age 49 and above group, predicted a difference only in the satisfaction dimension of employee engagement. Furthermore, the current bank experience indicated the difference in overall employee engagement. This study adds value to the literature as it contributes empirical evidence on integrative leadership and employee engagement. This study can be helpful for private banks, also for public & foreign banks and other organizations in Pakistan in adopting integrative leadership for enhancing employee engagement.

Download Full-text

Analisis Hubungan Kelimpahan Plankton di Permukaan Terhadap Hasil Tangkapan Ikan Lemuru (Sardinella lemuru) di Selat Bali

Journal of Marine and Aquatic Sciences ◽

10.24843/jmas.2018.v4.i01.151-161 ◽

2017 ◽

Vol 4 (1) ◽

pp. 151

Author(s):

Hasanuddin Parulian Sihombing ◽

I Gede Hendrawan ◽

Yulianto Suteja

Keyword(s):

Sampling Method ◽

Strong Relationship ◽

Zooplankton Abundance ◽

Sampling Point ◽

Water Sampling ◽

Phytoplankton Abundance ◽

Fish Food ◽

Area Sampling ◽

The Relationship

Lemuru fish is one of fishery commodity that has high economical value and one of fish that most catched by fisherman in Bali Strait. Lemuru fish had been caught in Bali Strait was fluctuating every month and every years. This condition was related with food source of Lemuru fish such as phytoplankton and zooplankton. So this research was conducted to explained the relationship phytoplankton and zooplankton abundance with Lemuru fish catched in Bali strait. This study focus in Bali strait during March until May 2017. Determination of sampling point used area sampling method while water sampling occured in surface water with pouring method. Total of phytoplankton and zooplankton abundance in Bali strait in March until May had formed the sinusoidal model with their abundance ranged 301 ind/L – 604 ind/L and 7 ind/L – 12 ind/L. Plankton abundance in Bali strait in March until May (transisonal season 1) was categorized low abundance if compared with plankton abundance in another season. The low value of phytoplankton abundance caused by non upwelling phenomenon and grazing process and the low abundance of zooplankton caused by low rate of zooplankton and predation by Lemuru fish. Phytoplankton and zooplankton abundance had strong relationship with Lemuru fish catched with correlation coefficient value 0.76 and 0.69. This condition caused by phytoplankton and zooplankton are source of Lemuru fish food.

Download Full-text

Pengaruh Penerapan Model Pembelajaran Kooperatif Tipe Course Review Horay (CRH) Terhadap Keaktifan Belajar dan Hasil Belajar Ekonomi

Soedirman Economics Education Journal ◽

10.32424/seej.v1i1.1939 ◽

2019 ◽

Vol 1 (1) ◽

pp. 1

Author(s):

Aisyah Aisyah

Keyword(s):

Learning Outcomes ◽

Sampling Method ◽

Learning Model ◽

Positive Influence ◽

Learning Activity ◽

Economic Study ◽

Purposive Sampling ◽

Significant Difference ◽

The Difference

This research is experimental research on students class XI of MIPA in SMA Negeri 3 Purwokerto. This research takes the title of "The Influence of the Application of the Cooperative Learning Model Type Course Review Horay (CRH) Against the Liveliness of learning and the Results of the Economic Study (study on the Grade XI MIPA in SMA Negeri 3 Purwokerto)". The purpose of this research is to know the difference in learning outcomes and learning activity between the learning model Course Review Horay (CRH) with conventional learning model, to know the influence of learning model Course Review Horay (CRH) against the learning outcomes and learning activity, as well as to know the influence of the liveliness of the learning results of learning. The population of this research is the grade XI MIPA in SMA Negeri 3 Purwokerto. The number of samples taken in this study is 72 i.e. 2 Class XI of MIPA which each class amounted to 36 students. Purposive Sampling Method used in the determination of the sample. Based on the results of the research and the anallisis data indicate that (1) there is a significant difference between the model of learning learning activeness cooperative Course Review Horay (CRH) and conventional learning model on economics. (2) there are significant differences between the learning outcomes learning model cooperative Course Review Horay (CRH) and conventional learning model on economi. (3) there is a positive influence learning model cooperative Course Review Horay (CRH) against the liveliness of the study on economic. (4) there is a positive influence learning model cooperative Course Review Horay (CRH) against the results of the study on economic. (5) there is no positive influence between the liveliness of student learning against the results of the study on economic. Penelitian ini adalah penelitian eksperimen pada siswa kelas XI MIPA di SMA Negeri 3 Purwokerto. Penelitian ini mengambil judul “Pengaruh Penerapan Model Pembelajaran Kooperatif Tipe Course Review Horay (CRH) terhadap Keaktifan Belajar dan Hasil Belajar Ekonomi (Studi pada Siswa Kelas XI MIPA di SMA Negeri 3 Purwokerto)”. Tujuan dari penelitian ini adalah untuk mengetahui perbedaan keaktifan belajar dan hasil belajar antara model pembelajaran Course Review Horay (CRH) dengan model pembelajaran konvensional, untuk mengetahui pengaruh model pembelajaran Course Review Horay (CRH) terhadap keaktifan belajar dan hasil belajar, serta untuk mengetahui pengaruh keaktifan belajar terhadap hasil belajar. Populasi penelitian ini adalah siswa kelas XI MIPA di SMA Negeri 3 Purwokerto. Jumlah sample yang diambil dalam penelitian ini adalah 72 yaitu 2 kelas XI MIPA yang masing-masing kelas berjumlah 36 siswa. Purposive Sampling Method digunakan dalam penentuan sample. Berdasarkan hasil penelitian dan anallisis data menunjukkan bahwa (1) Terdapat perbedaan signifikan keaktifan belajar antara model pembelajaran kooperatif Course Review Horay (CRH) dengan model pembelajaran konvensional pada mata pelajaran ekonomi. (2) Terdapat perbedaan signifikan hasil belajar antara model pembelajaran kooperatif Course Review Horay (CRH) dengan model pembelajaran konvensional pada mata pelajaran ekonomi. (3) Terdapat pengaruh positif model pembelajaran kooperatif Course Review Horay (CRH) terhadap keaktifan belajar pada mata pelajaran ekonomi. (4) Terdapat pengaruh positif model pembelajaran kooperatif Course Review Horay (CRH) terhadap hasil belajar pada mata pelajaran ekonomi. (5) Tidak terdapat pengaruh positif antara keaktifan belajar siswa terhadap hasil belajar pada mata pelajaran ekonomi.

Download Full-text