1/9/2024 0 Comments Finger spelling alphabetDenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. ![]() For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. Whereas traditional convolutional networks with L layers have L connections - one between each layer and its subsequent layer - our network has L(L+1)/2 direct connections. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. Two possible real time applications are conducted, one is for interpretation of ASL sign alphabets and another is for Image browsing. The experimental result is evaluated in terms of mean accuracy. All above three datasets are developed based on American Sign Language (ASL) hand alphabets. The performance of the proposed method is evaluated on two standard public datasets and one indigenously developed complex background dataset for recognition of hand gestures. A linear support vector machine (SVM) is used as a classifier to recognize the hand gestures. This method is not only robust towards distortion and gesture vocabulary, but also invariant to translation and rotation of hand gestures. This work proposes a discrete wavelet transform (DWT) and Fisher ratio (F-ratio) based feature extraction technique to classify the hand gestures in an uncontrolled environment. The preprocessing stage consists of illumination compensation, segmentation, filtering, hand region detection and image resize. The vision based static hand gesture recognition system is developed using the following steps: preprocessing, feature extraction and classification. ![]() This paper demonstrates the development of vision based static hand gesture recognition system using web camera in real time applications. ![]() The performance of the proposed network is evaluated on the standard datasets: MUGD, Finger Spelling, OUHands, NUS-I, NUS-II and HGR1 for both subject-dependent and subject-independent scheme. Thus, the proposed ExtriDeNet efficiently defines the distinctive features of different hand gesture classes and achieves high performance as compared to state-of-the-art HGR approaches. The combination of multiscaled filters enriches the network with the most significant features and enhances the learnability of the network. IFFB incorporates two different scaled filters 3×3 and 5×5 to capture contextual features of hands, while IFAB is designed by embedding influential features of IFFB with two extreme minute and high-level feature responses from two receptive fields generated by employing 1×1 and 7×7 sized filters, respectively. ExtriDeNet primarily consists of two blocks: Intensive Feature Fusion Block (IFFB) and Intensive Feature Assimilation Block (IFAB). In this paper, a lightweighted Intensive Feature Extrication Deep Network (ExtriDeNet) is proposed for precise hand gesture recognition (HGR). The experimental results are evaluated using a subject-independent cross-validation test on three benchmarked datasets and compared with the earlier reported techniques. After extracting the RBI features, a linear kernel-based multi-class support vector machine classifier is used to recognize the gesture poses. Motivated by the above facts, this work proposes (i) a two-stage residual CNN (2RCNN) architecture for learning of features from the color hand gesture images which overcomes the need of a specific preprocessing step, (ii) a novel residual block intensity (RBI) feature to extract the global and local information from the hand gesture images. ![]() Therefore, a CNN-based HGR paradigm can be developed with less number of layers and feature fusion with global and local information from different layers. However, the architecture of CNN is complex and the extracted deep feature from these networks provides the global information only. The convolutional neural networks (CNNs) can handle the less generalization characteristic of the handcrafted techniques. The performance of the existing handcrafted techniques relies on the less generalized preprocessing and feature extraction steps. Hand gesture recognition (HGR) is the most effective and intuitive way for the human–computer interface used in various applications, such as sign language recognition, robotics, and multimedia applications.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |