scholarly journals A Deep Convolutional Neural Network Approach to Sign Alphabet Recognition

2021 ◽  
pp. 172-182
Author(s):  
Uday Kumar Adusumilli ◽  
Sanjana M S ◽  
Teja S ◽  
Yashawanth K M ◽  
Raghavendra R ◽  
...  
Keyword(s):  
Neural Networks ◽  
Sign Language ◽  
Convolutional Neural Networks ◽  
Skin Color ◽  
Color Space ◽  
Test Accuracy ◽  
Hand Detection ◽  
Deep Convolutional Neural Networks ◽  
Neural Network Approach ◽  
Real Time Processing

In this paper, we present an application that has been developed to be used as a tool for the purposes of learning sign language for beginners that utilizes hand detection as part of the process. It uses a skin-color modelling technique, such as explicit thresholding in the skin-color space, which is based on modeling skin-color spaces. This predetermined range of skin-colors is used to determine how pixels (hand) will be extracted from non-pixels (background). To classify the images, convolutional neural networks (CNN) were fed the images for the creation of the classifier. The training of the images was done using Keras. A uniform background and proper lighting conditions enabled the system to achieve a test accuracy of 93.67%, of which 90.04% was attributed to ASL alphabet recognition, 93.44% for number recognition and 97.52% recognition of static words, surpassing other studies of the type. An approach which is based on this technique is used for fast computation as well as real-time processing. Deaf-dumb people face a number of social challenges as the communication barrier prevents them from accessing basic and essential services of the life that they are entitled to as members of the hearing community. In spite of the fact that a number of factors have been incorporated into the innovations in the automatic recognition of sign language, an adequate solution has yet to be reached because of a number of challenges. As far as I know, the vast majority of existing works focus on developing vision based recognizers by deriving complex feature descriptors from captured images of the gestures and applying a classical pattern analysis technique. Although utilizing these methods can be effective when dealing with small sign vocabulary captures with a complex and uncontrolled background, they are very limited when dealing with large sign vocabulary. This paper proposes a method for analyzing and representing hand gestures, which acts as the core component of the vocabulary for signing languages, using a deep convolutional neural networks (CNN) architecture. On two publicly accessible datasets (the NUS hand posture dataset and the American fingerspelling A dataset), the method was demonstrated to be more accurate in recognizing hand postures.

scholarly journals Identifying Habitat Elements from Bird Images Using Deep Convolutional Neural Networks

Animals ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 1263
Author(s):  
Zhaojun Wang ◽  
Jiangning Wang ◽  
Congtian Lin ◽  
Yan Han ◽  
Zhaosheng Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Digital Technology ◽  
Rapid Development ◽  
Image Data ◽  
Image Database ◽  
Test Accuracy ◽  
Practical Application ◽  
Accuracy Rate ◽  
Deep Convolutional Neural Networks

With the rapid development of digital technology, bird images have become an important part of ornithology research data. However, due to the rapid growth of bird image data, it has become a major challenge to effectively process such a large amount of data. In recent years, deep convolutional neural networks (DCNNs) have shown great potential and effectiveness in a variety of tasks regarding the automatic processing of bird images. However, no research has been conducted on the recognition of habitat elements in bird images, which is of great help when extracting habitat information from bird images. Here, we demonstrate the recognition of habitat elements using four DCNN models trained end-to-end directly based on images. To carry out this research, an image database called Habitat Elements of Bird Images (HEOBs-10) and composed of 10 categories of habitat elements was built, making future benchmarks and evaluations possible. Experiments showed that good results can be obtained by all the tested models. ResNet-152-based models yielded the best test accuracy rate (95.52%); the AlexNet-based model yielded the lowest test accuracy rate (89.48%). We conclude that DCNNs could be efficient and useful for automatically identifying habitat elements from bird images, and we believe that the practical application of this technology will be helpful for studying the relationships between birds and habitat elements.

scholarly journals Understanding unconventional preprocessors in deep convolutional neural networks for face identification

2019 ◽  
Vol 1 (11) ◽  
Author(s):  
Chollette C. Olisah ◽  
Lyndon Smith
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Color Space ◽  
Back Propagation ◽  
Face Identification ◽  
Deep Convolutional Neural Networks ◽  
Softmax Classifier ◽  
Deep Network

Abstract Deep convolutional neural networks have achieved huge successes in application domains like object and face recognition. The performance gain is attributed to different facets of the network architecture such as: depth of the convolutional layers, activation function, pooling, batch normalization, forward and back propagation and many more. However, very little emphasis is made on the preprocessor’s module of the network. Therefore, in this paper, the network’s preprocessing module is varied across different preprocessing approaches while keeping constant other facets of the deep network architecture, to investigate the contribution preprocessing makes to the network. Commonly used preprocessors are the data augmentation and normalization and are termed conventional preprocessors. Others are termed the unconventional preprocessors, they are: color space converters; grey-level resolution preprocessors; full-based and plane-based image quantization, Gaussian blur, illumination normalization and insensitive feature preprocessors. To achieve fixed network parameters, CNNs with transfer learning is employed. The aim is to transfer knowledge from the high-level feature vectors of the Inception-V3 network to offline preprocessed LFW target data; and features is trained using the SoftMax classifier for face identification. The experiments show that the discriminative capability of the deep networks can be improved by preprocessing RGB data with some of the unconventional preprocessors before feeding it to the CNNs. However, for best performance, the right setup of preprocessed data with augmentation and/or normalization is required. Summarily, preprocessing data before it is fed to the deep network is found to increase the homogeneity of neighborhood pixels even at reduced bit depth which serves for better storage efficiency.

scholarly journals Detection of Fuchs’ Uveitis Syndrome From Slit-Lamp Images Using Deep Convolutional Neural Networks in a Chinese Population

2021 ◽  
Vol 9 ◽  
Author(s):  
Wanyun Zhang ◽  
Zhijun Chen ◽  
Han Zhang ◽  
Guannan Su ◽  
Rui Chang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Independent Set ◽  
Network Models ◽  
Test Accuracy ◽  
Slit Lamp ◽  
Deep Convolutional Neural Networks ◽  
Receiver Operating Characteristic Curves ◽  
Optimized Model ◽  
Fuchs Uveitis Syndrome

Fuchs’ uveitis syndrome (FUS) is one of the most under- or misdiagnosed uveitis entities. Many undiagnosed FUS patients are unnecessarily overtreated with anti-inflammatory drugs, which may lead to serious complications. To offer assistance for ophthalmologists in the screening and diagnosis of FUS, we developed seven deep convolutional neural networks (DCNNs) to detect FUS using slit-lamp images. We also proposed a new optimized model with a mixed “attention” module to improve test accuracy. In the same independent set, we compared the performance between these DCNNs and ophthalmologists in detecting FUS. Seven different network models, including Xception, Resnet50, SE-Resnet50, ResNext50, SE-ResNext50, ST-ResNext50, and SET-ResNext50, were used to predict FUS automatically with the area under the receiver operating characteristic curves (AUCs) that ranged from 0.951 to 0.977. Our proposed SET-ResNext50 model (accuracy = 0.930; Precision = 0.918; Recall = 0.923; F1 measure = 0.920) with an AUC of 0.977 consistently outperformed the other networks and outperformed general ophthalmologists by a large margin. Heat-map visualizations of the SET-ResNext50 were provided to identify the target areas in the slit-lamp images. In conclusion, we confirmed that a trained classification method based on DCNNs achieved high effectiveness in distinguishing FUS from other forms of anterior uveitis. The performance of the DCNNs was better than that of general ophthalmologists and could be of value in the diagnosis of FUS.

scholarly journals Using Deep Convolutional Neural Networks for Image-Based Diagnosis of Nutrient Deficiencies in Rice

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Zhe Xu ◽  
Xi Guo ◽  
Anfan Zhu ◽  
Xiaolin He ◽  
Xiaomin Zhao ◽  
...  
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Fine Tuning ◽  
Support Vector ◽  
Test Accuracy ◽  
Nutrient Deficiencies ◽  
Deep Convolutional Neural Networks ◽  
Histogram Of Oriented Gradient

Symptoms of nutrient deficiencies in rice plants often appear on the leaves. The leaf color and shape, therefore, can be used to diagnose nutrient deficiencies in rice. Image classification is an efficient and fast approach for this diagnosis task. Deep convolutional neural networks (DCNNs) have been proven to be effective in image classification, but their use to identify nutrient deficiencies in rice has received little attention. In the present study, we explore the accuracy of different DCNNs for diagnosis of nutrient deficiencies in rice. A total of 1818 photographs of plant leaves were obtained via hydroponic experiments to cover full nutrition and 10 classes of nutrient deficiencies. The photographs were divided into training, validation, and test sets in a 3 : 1 : 1 ratio. Fine-tuning was performed to evaluate four state-of-the-art DCNNs: Inception-v3, ResNet with 50 layers, NasNet-Large, and DenseNet with 121 layers. All the DCNNs obtained validation and test accuracies of over 90%, with DenseNet121 performing best (validation accuracy = 98.62 ± 0.57%; test accuracy = 97.44 ± 0.57%). The performance of the DCNNs was validated by comparison to color feature with support vector machine and histogram of oriented gradient with support vector machine. This study demonstrates that DCNNs provide an effective approach to diagnose nutrient deficiencies in rice.

scholarly journals Better Communication Tool for Specially Disabled

2019 ◽  
Vol 8 (4) ◽  
pp. 3008-3011
Keyword(s):  
Neural Networks ◽  
Sign Language ◽  
Convolutional Neural Networks ◽  
Time Lapse ◽  
Normal Person ◽  
Communication Tool ◽  
Deep Convolutional Neural Networks ◽  
Detection Model ◽  
Pruning Strategy ◽  
Speed Up

Sign language is widely used when a dumb communicates. However, non-sign-language people find it difficult in interpreting them. So, we had come up with a system that enables speech impaired to speak with an artificial voice in public communities using Artificial intelligence techniques. we propose a hybrid-weighted metric known as weighted pruning in deep convolutional neural networks. In this work, we report experiments of weighted pruning. we show that using a weighted pruning strategy we can achieve significant speed up in Faster RCNN object detection model by discarding 50% of filters. In this paper we show evidences to our claim by reporting mean Average Precision of weighted pruned CNN is slightly higher than existing pruning techniques. The former part of the paper focus on moulding convolutional neural networks in terms of their speed and scalability for deploying them on mobiles, embedded and further small gadgets. The latter part of the paper describes novel approaches in letting dumb speak as fast as normal person in public, without time lapse using natural language algorithms and recommendations.

Sign in / Sign up

Export Citation Format

Share Document