Using Deep Convolutional Neural Network in Computer Vision for Real-World Scene Classification

The aim of this study was to investigate the potential of a machine learning algorithm to accurately classify parenchymal density in spiral breast-CT (BCT), using a deep convolutional neural network (dCNN). In this retrospectively designed study, 634 examinations of 317 patients were included. After image selection and preparation, 5589 images from 634 different BCT examinations were sorted by a four-level density scale, ranging from A to D, using ACR BI-RADS-like criteria. Subsequently four different dCNN models (differences in optimizer and spatial resolution) were trained (70% of data), validated (20%) and tested on a “real-world” dataset (10%). Moreover, dCNN accuracy was compared to a human readout. The overall performance of the model with lowest resolution of input data was highest, reaching an accuracy on the “real-world” dataset of 85.8%. The intra-class correlation of the dCNN and the two readers was almost perfect (0.92) and kappa values between both readers and the dCNN were substantial (0.71–0.76). Moreover, the diagnostic performance between the readers and the dCNN showed very good correspondence with an AUC of 0.89. Artificial Intelligence in the form of a dCNN can be used for standardized, observer-independent and reliable classification of parenchymal density in a BCT examination.

Download Full-text

High Spatial Resolution Remote Sensing Scene Classification Method using Transfer Learning and Deep Convolutional Neural Network

10.36227/techrxiv.11694966.v1 ◽

2020 ◽

Author(s):

Wenmei Li ◽

Juan Wang ◽

Ziteng Wang ◽

Yu Wang ◽

Yan Jia ◽

...

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Spatial Resolution ◽

High Spatial Resolution ◽

Deep Convolutional Neural Network ◽

Classification Method ◽

Scene Classification ◽

High Quality

Deep convolutional neural network (DeCNN) is considered one of promising techniques for classifying the high spatial resolution remote sensing (HSRRS) scenes, due to its powerful feature extraction capabilities. It is well-known that huge high quality labeled datasets are required for achieving the better classification performances and preventing over-fitting, during the training DeCNN model process. However, the lack of high quality datasets often limits the applications of DeCNN. In order to solve this problem, in this paper, we propose a HSRRS image scene classification method using transfer learning and DeCNN (TL-DeCNN) model in few shot HSRRS scene samples. Specifically, three typical DeCNNs of VGG19, ResNet50 and InceptionV3, trained on the ImageNet2015, the weights of their convolutional layer for that of the TL-DeCNN are transferred, respectively. Then, TL-DeCNN just needs to fine-tune its classification module on the few shot HSRRS scene samples in a few epochs. Experimental results indicate that our proposed TL-DeCNN method provides absolute dominance results without over-fitting, when compared with the VGG19, ResNet50 and InceptionV3, directly trained on the few shot samples.

Download Full-text

High Spatial Resolution Remote Sensing Scene Classification Method using Transfer Learning and Deep Convolutional Neural Network

10.36227/techrxiv.11694966 ◽

2020 ◽

Author(s):

Wenmei Li ◽

Juan Wang ◽

Ziteng Wang ◽

Yu Wang ◽

Yan Jia ◽

...

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Spatial Resolution ◽

High Spatial Resolution ◽

Deep Convolutional Neural Network ◽

Classification Method ◽

Scene Classification ◽

High Quality

Deep convolutional neural network (DeCNN) is considered one of promising techniques for classifying the high spatial resolution remote sensing (HSRRS) scenes, due to its powerful feature extraction capabilities. It is well-known that huge high quality labeled datasets are required for achieving the better classification performances and preventing over-fitting, during the training DeCNN model process. However, the lack of high quality datasets often limits the applications of DeCNN. In order to solve this problem, in this paper, we propose a HSRRS image scene classification method using transfer learning and DeCNN (TL-DeCNN) model in few shot HSRRS scene samples. Specifically, three typical DeCNNs of VGG19, ResNet50 and InceptionV3, trained on the ImageNet2015, the weights of their convolutional layer for that of the TL-DeCNN are transferred, respectively. Then, TL-DeCNN just needs to fine-tune its classification module on the few shot HSRRS scene samples in a few epochs. Experimental results indicate that our proposed TL-DeCNN method provides absolute dominance results without over-fitting, when compared with the VGG19, ResNet50 and InceptionV3, directly trained on the few shot samples.

Download Full-text

An Optimized Approach for Intra-Class Fruit Classification Using Deep Convolutional Neural Network

International Journal of Image and Graphics ◽

10.1142/s0219467821400143 ◽

2021 ◽

pp. 2140014

Author(s):

Rishipal Singh ◽

Rajneesh Rani ◽

Aman Kamboj

Keyword(s):

Neural Network ◽

Computer Vision ◽

Convolutional Neural Network ◽

State Of The Art ◽

Deep Convolutional Neural Network ◽

Classification Models ◽

Proposed Model ◽

Traditional Classification

Fruits classification is one of the influential applications of computer vision. Traditional classification models are trained by considering various features such as color, shape, texture, etc. These features are common for different varieties of the same fruit. Therefore, a new set of features is required to classify the fruits belonging to the same class. In this paper, we have proposed an optimized method to classify intra-class fruits using deep convolutional layers. The proposed architecture is capable of solving the challenges of a commercial tray-based system in the supermarket. As the research in intra-class classification is still in its infancy, there are challenges that have not been tackled. So, the proposed method is specifically designed to overcome the challenges related to intra-class fruits classification. The proposed method showcases an impressive performance for intra-class classification, which is achieved using a few parameters than the existing methods. The proposed model consists of Inception block, Residual connections and various other layers in very precise order. To validate its performance, the proposed method is compared with state-of-the-art models and performs best in terms of accuracy, loss, parameters, and depth.

Download Full-text

AUTOMATIC PARENTAL GUIDE SCENE CLASSIFICATION MENGGUNAKAN METODE DEEP CONVOLUTIONAL NEURAL NETWORK DAN LSTM

Journal of Intelligent System and Computation ◽

10.52985/insyst.v2i2.124 ◽

2020 ◽

Vol 2 (2) ◽

pp. 86-90

Author(s):

Riko Gunawan ◽

Yosi Kristian

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Deep Convolutional Neural Network ◽

Scene Classification

Menonton film merupakan salah satu hobi yang paling digemari oleh berbagai kalangan. Seiring dengan semakin bertambahnya film yang beredar di pasaran, semakin banyak pula konten tidak pantas pada film-film tersebutu. Oleh karena itu, dibutuhkan sebuah metode untuk mengklasifikasikan film agar konten yang ditonton sesuai dengan usia penonton. Konten film yang kurang cocok untuk pengguna di bawah umur yang akan diklasifikasikan pada penelitian ini antara lain: kekerasan, pronografi, kata-kata kasar, minuman keras, penggunaan obat-obatan terlarang, merokok, adegan mengerikan (horror) dan intens. Metode klasifikasi yang digunakan berupa modifikasi dari convolutional neural network dan LSTM. Gabungan kedua metode ini dapat mengakomodasi data training dalam jumlah yang kecil, serta dapat melakukan multi klasifikasi berdasarkan video, audio, dan subtitle film. Penggunaan multi klasifikasi ini dikarenakan sebuah film selalu memiliki lebih dari satu klasifikasi. Dalam proses training dan testing pada penelitian ini digunakan sebanyak 1000 data untuk klasifikasi video, 600 data klasifikasi audio, dan 400 data klasifikasi subtitle yang didapatkan dari internet. Dari hasil percobaan dihasilkan tingkat akurasi yang diukur dengan menggunakan F1-Score sebesar 0.922 untuk klasifikasi video, 0.741 untuk klasifikasi audio, dan 0.844 untuk klasifikasi subtitle dengan rata-rata akurasi sebesar 0.835. Pada penelitian berikutnya akan dicoba dengan menggunakan metode Deep Convolutional Neural Network yang lain serta dengan memperbanyak jumlah dan variasi dari data testing.

Download Full-text

Midwave FTIR-Based Remote Surface Temperature Estimation Using a Deep Convolutional Neural Network in a Dynamic Weather Environment

Micromachines ◽

10.3390/mi9100495 ◽

2018 ◽

Vol 9 (10) ◽

pp. 495 ◽

Cited By ~ 3

Author(s):

Sungho Kim ◽

Jungho Kim ◽

Jinyong Lee ◽

Junmo Ahn

Keyword(s):

Neural Network ◽

Surface Temperature ◽

Convolutional Neural Network ◽

Real Time ◽

Real World ◽

Hyperspectral Image ◽

Estimation Method ◽

Deep Convolutional Neural Network ◽

Temperature Estimation ◽

Midwave Infrared

Remote measurements of thermal radiation are very important for analyzing the solar effect in various environments. This paper presents a novel real-time remote temperature estimation method by applying a deep learning-based regression method to midwave infrared hyperspectral images. A conventional remote temperature estimation using only one channel or multiple channels cannot provide a reliable temperature in dynamic weather environments because of the unknown atmospheric transmissivities. This paper solves the issue (real-time remote temperature measurement with high accuracy) with the proposed surface temperature-deep convolutional neural network (ST-DCNN) and a hyperspectral thermal camera (TELOPS HYPER-CAM MWE). The 27-layer ST-DCNN regressor can learn and predict the underlying temperatures from 75 spectral channels. Midwave infrared hyperspectral image data of a remote object were acquired three times a day (10:00, 13:00, 15:00) for 7 months to consider the dynamic weather variations. The experimental results validate the feasibility of the novel remote temperature estimation method in real-world dynamic environments. In addition, the thermal stealth properties of two types of paint were demonstrated by the proposed ST-DCNN as a real-world application.

Download Full-text