scholarly journals A NEW APPROACH FOR URBAN ROADS DETECTION USING LASER DATA AND AERIAL DIGITAL IMAGES

2016 ◽  
Vol 10 (1) ◽  
pp. 83-97
Author(s):  
Francisco Assis Da Silva ◽  
Anderson Akio Gohara ◽  
Mário Augusto Pazoti ◽  
Danillo Roberto Pereira ◽  
Almir Olivette Artero ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Digital Image ◽  
Aerial Images ◽  
Automatic Extraction ◽  
New Approach ◽  
Additional Information ◽  
Automatic Feature Extraction ◽  
Laser Data ◽  
Sensitivity Rate ◽  
Road Segments

The automatic feature extraction from digital aerial images is not a trivial task mainly due to occlusion problems, shadows and different viewpoints. To obtain an improved feature extraction we used laser data, which have additional information such as height and material type of the surface. In this paper we performed the combination of digital image and laser data in order to improve the results of automatic extraction of urban roads. Initially, the urban roads were detected from the response of laser information; in the sequence we applied two different approaches to connect the disconnected road segments. The results were very promising, with sensitivity rate of 92%.

scholarly journals A NEW APPROACH FOR URBAN ROADS DETECTION USING LASER DATA AND AERIAL DIGITAL IMAGES

2016 ◽  
Vol 10 (1) ◽  
pp. 83-97 ◽  
Author(s):  
Francisco Assis Da Silva ◽  
Anderson Akio Gohara ◽  
Mário Augusto Pazoti ◽  
Danillo Roberto Pereira ◽  
Almir Olivette Artero ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Digital Image ◽  
Aerial Images ◽  
Automatic Extraction ◽  
New Approach ◽  
Additional Information ◽  
Automatic Feature Extraction ◽  
Laser Data ◽  
Sensitivity Rate ◽  
Road Segments

The automatic feature extraction from digital aerial images is not a trivial task mainly due to occlusion problems, shadows and different viewpoints. To obtain an improved feature extraction we used laser data, which have additional information such as height and material type of the surface. In this paper we performed the combination of digital image and laser data in order to improve the results of automatic extraction of urban roads. Initially, the urban roads were detected from the response of laser information; in the sequence we applied two different approaches to connect the disconnected road segments. The results were very promising, with sensitivity rate of 92%.

scholarly journals A New Approach to Reducing the Distortion of the Digital Image Natural Model in the DCT Domain When Embedding Information According to the QIM Method

2019 ◽  
Author(s):  
Олег Евсютин ◽  
Oleg Evsutin ◽  
Анна Мельман ◽  
Anna Melman ◽  
Роман Мещеряков ◽  
...  
Keyword(s):  
Image Processing ◽  
Digital Image ◽  
Digital Content ◽  
The Internet ◽  
Embedding Capacity ◽  
New Approach ◽  
Additional Information ◽  
Dct Domain ◽  
Dct Coefficients ◽  
Information Confidentiality

One of the areas of digital image processing is the steganographic embedding of additional information into them. Digital steganography methods are used to ensure the information confidentiality, as well as to track the distribution of digital content on the Internet. Main indicators of the steganographic embedding effectiveness are invisibility to the human eye, characterized by the PSNR metric, and embedding capacity. However, even with full visual stealth of embedding, its presence may produce a distortion of the digital image natural model in the frequency domain. The article presents a new approach to reducing the distortion of the digital image natural model in the field of discrete cosine transform (DCT) when embedding information using the classical QIM method. The results of the experiments show that the proposed approach allows reducing the distortion of the histograms of the distribution of DCT coefficients, and thereby eliminating the unmasking signs of embedding.

scholarly journals Evolving deep forest with automatic feature extraction for image classification using genetic programming

2020 ◽  
Author(s):  
Ying Bi ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Feature Extraction ◽  
Genetic Programming ◽  
Image Classification ◽  
Random Forests ◽  
Back Propagation ◽  
Image Features ◽  
New Approach ◽  
Automatic Feature Extraction ◽  
Deep Forest ◽  
Encoding Strategy

© Springer Nature Switzerland AG 2020. Deep forest is an alternative to deep neural networks to use multiple layers of random forests without back-propagation for solving various problems. In this study, we propose a genetic programming-based approach to automatically and simultaneously evolving effective structures of deep forest connections and extracting informative features for image classification. First, in the new approach we define two types of modules: forest modules and feature extraction modules. Second, an encoding strategy is developed to integrate forest modules and feature extraction modules into a tree and the search strategy is introduced to search for the best solution. With these designs, the proposed approach can automatically extract image features and find forests with effective structures simultaneously for image classification. The parameters in the forest can be dynamically determined during the learning process of the new approach. The results show that the new approach can achieve better performance on the datasets having a small number of training instances and competitive performance on the datasets having a large number of training instances. The analysis of evolved solutions shows that the proposed approach uses a smaller number of random forests over the deep forest method.

scholarly journals Evolving deep forest with automatic feature extraction for image classification using genetic programming

2020 ◽  
Author(s):  
Ying Bi ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Feature Extraction ◽  
Genetic Programming ◽  
Image Classification ◽  
Random Forests ◽  
Back Propagation ◽  
Image Features ◽  
New Approach ◽  
Automatic Feature Extraction ◽  
Deep Forest ◽  
Encoding Strategy

© Springer Nature Switzerland AG 2020. Deep forest is an alternative to deep neural networks to use multiple layers of random forests without back-propagation for solving various problems. In this study, we propose a genetic programming-based approach to automatically and simultaneously evolving effective structures of deep forest connections and extracting informative features for image classification. First, in the new approach we define two types of modules: forest modules and feature extraction modules. Second, an encoding strategy is developed to integrate forest modules and feature extraction modules into a tree and the search strategy is introduced to search for the best solution. With these designs, the proposed approach can automatically extract image features and find forests with effective structures simultaneously for image classification. The parameters in the forest can be dynamically determined during the learning process of the new approach. The results show that the new approach can achieve better performance on the datasets having a small number of training instances and competitive performance on the datasets having a large number of training instances. The analysis of evolved solutions shows that the proposed approach uses a smaller number of random forests over the deep forest method.

RESEARCH ON AUTOMATIC EXTRACTION OF DEFOCUS IMAGES IN UAV AERIAL IMAGES

2019 ◽  
Vol 75 (2) ◽  
pp. I_106-I_113
Author(s):  
Etsuji KITAGAWA ◽  
Ryo KATO ◽  
Satoshi ABIKO ◽  
Takumi TSUMURA ◽  
Yusuke NAKATANI
Keyword(s):  
Aerial Images ◽  
Automatic Extraction

scholarly journals Underwater Acoustic Target Recognition Based on Depthwise Separable Convolution Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1429
Author(s):  
Gang Hu ◽  
Kejun Wang ◽  
Liangliang Liu
Keyword(s):  
Feature Extraction ◽  
Target Recognition ◽  
Target Feature ◽  
Underwater Acoustic ◽  
Radiated Noise ◽  
Automatic Feature Extraction ◽  
Acoustic Target ◽  
And Cluster Analysis ◽  
Underwater Target ◽  
The One

Facing the complex marine environment, it is extremely challenging to conduct underwater acoustic target feature extraction and recognition using ship-radiated noise. In this paper, firstly, taking the one-dimensional time-domain raw signal of the ship as the input of the model, a new deep neural network model for underwater target recognition is proposed. Depthwise separable convolution and time-dilated convolution are used for passive underwater acoustic target recognition for the first time. The proposed model realizes automatic feature extraction from the raw data of ship radiated noise and temporal attention in the process of underwater target recognition. Secondly, the measured data are used to evaluate the model, and cluster analysis and visualization analysis are performed based on the features extracted from the model. The results show that the features extracted from the model have good characteristics of intra-class aggregation and inter-class separation. Furthermore, the cross-folding model is used to verify that there is no overfitting in the model, which improves the generalization ability of the model. Finally, the model is compared with traditional underwater acoustic target recognition, and its accuracy is significantly improved by 6.8%.

scholarly journals Image Classification for the Automatic Feature Extraction in Human Worn Fashion Data

Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 624
Author(s):  
Stefan Rohrmanstorfer ◽  
Mikhail Komarov ◽  
Felix Mödritscher
Keyword(s):  
Neural Networks ◽  
Feature Extraction ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Image Data ◽  
Classification Model ◽  
Upper Body ◽  
Automatic Feature Extraction

With the always increasing amount of image data, it has become a necessity to automatically look for and process information in these images. As fashion is captured in images, the fashion sector provides the perfect foundation to be supported by the integration of a service or application that is built on an image classification model. In this article, the state of the art for image classification is analyzed and discussed. Based on the elaborated knowledge, four different approaches will be implemented to successfully extract features out of fashion data. For this purpose, a human-worn fashion dataset with 2567 images was created, but it was significantly enlarged by the performed image operations. The results show that convolutional neural networks are the undisputed standard for classifying images, and that TensorFlow is the best library to build them. Moreover, through the introduction of dropout layers, data augmentation and transfer learning, model overfitting was successfully prevented, and it was possible to incrementally improve the validation accuracy of the created dataset from an initial 69% to a final validation accuracy of 84%. More distinct apparel like trousers, shoes and hats were better classified than other upper body clothes.

Research on Feature Extraction and Optimization of Cashmere and Wool Fiber Based on Digital Image

2014 ◽  
Vol 667 ◽  
pp. 260-263 ◽  
Author(s):  
Heng Chen ◽  
Ya Xia Liu
Keyword(s):  
Feature Extraction ◽  
Digital Image ◽  
Textile Industry ◽  
Recognition Rate ◽  
Wool Fiber

The identification of cashmere and wool fiber is one of the difficult problems in the textile industry. Three features including diameter, diameter shaft parameter and the density are extracted using MATLAB.Support vector machine is used to recognition the cashmere and wool fiber. The experiment shows that diameter is not a useful feature for recognition and density combined diameter shaft parameter is useful for differentiate them and recognition rate is 87.35%.

Sign in / Sign up

Export Citation Format

Share Document