Sketch recognition

About: Sketch recognition is a research topic. Over the lifetime, 1611 publications have been published within this topic receiving 40284 citations.

Deep CNN-based Features for Hand-Drawn Sketch Recognition via Transfer Learning Approach

Abstract: Image-based object recognition is a well-studied topic in the field of computer vision. Features extraction for hand-drawn sketch recognition and retrieval become increasingly popular among the computer vision researchers. Increasing use of touchscreens and portable devices raised the challenge for computer vision community to access the sketches more efficiently and effectively. In this article, a novel deep convolutional neural network-based (DCNN) framework for hand-drawn sketch recognition, which is composed of three well-known pre-trained DCNN architectures in the context of transfer learning with global average pooling (GAP) strategy is proposed. First, an augmented-variants of natural images was generated and sum-up with TU-Berlin sketch images to all its corresponding 250 sketch object categories. Second, the features maps were extracted by three asymmetry DCNN architectures namely, Visual Geometric Group Network (VGGNet), Residual Networks (ResNet) and Inception-v3 from input images. Finally, the distinct features maps were concatenated and the features reductions were carried out under GAP layer. The resulting feature vector was fed into the softmax classifier for sketch classification results. The performance of proposed framework is comprehensively evaluated on augmented-variants TU-Berlin sketch dataset for sketch classification and retrieval task. Experimental outcomes reveal that the proposed framework brings substantial improvements over the state-of-the-art methods for sketch classification and retrieval.

Vision based gesturally controllable human computer interaction system

Abstract: Human computer interaction with simple hand gesture recognition system as the interface using computer vision techniques has been developed. Usage of visually interpreted hand gestures as the interface makes it a more natural and intuitive human computer interaction (HCI) system. In this system model, interfacing by traditional methods in virtual environments like a joystick, mouse, and keyboard and even if the modern method like touch screen is also replaced by using hand gestures. Here the computer is able to visually recognize hand gestures from the video obtained using a webcam. In the hand gesture recognition system, the skin colour thresholding model is used for segmentation. Various features are extracted and then classified using an efficient classifier to generate more accurate and better result. Apart from HCI, this vision based hand gesture recognition can also be used for applications like industrial robot control, sign language translation, in the rehabilitation device for people with upper extremity physical impairments etc.

Learning Semantic Features For Visual Recognition

Abstract: Visual recognition (e.g., object, scene and action recognition) is an active area of research in computer vision due to its increasing number of real-world applications such as video (image) indexing and search, intelligent surveillance, human-machine interaction, robot navigation, etc. Effective modeling of the objects, scenes and actions is critical for visual recognition. Recently, bag of visual words (BoVW) representation, in which the image patches or video cuboids are quantized into visual words (i.e., mid-level features) based on their appearance similarity using clustering, has been widely and successfully explored. The advantages of this representation are: no explicit detection of objects or object parts and their tracking are required; the representation is somewhat tolerant to within-class deformations, and it is efficient for matching. However, the performance of the BoVW is sensitive to the size of the visual vocabulary. Therefore, computationally expensive cross-validation is needed to find the appropriate quantization granularity. This limitation is partially due to the fact that the visual words are not semantically meaningful. This limits the effectiveness and compactness of the representation. To overcome these shortcomings, in this thesis we present principled approach to learn a semantic vocabulary (i.e. high-level features) from a large amount of visual words (mid-level features). In this context, the thesis makes two major contributions. First, we have developed an algorithm to discover a compact yet discriminative semantic vocabulary. This vocabulary is obtained by grouping the visual-words based on their distribution in videos (images) into visual-word clusters. The mutual information (MI) between the clusters and the videos (images) depicts the discriminative power of the semantic vocabulary, while the MI between visual-words and visual-word clusters measures the compactness of the vocabulary. We apply the information bottleneck (IB) algorithm to find the optimal number of visual-word clusters by finding the good tradeoff between compactness and discriminative power. We tested our proposed approach on the state-of-the-art KTH

Recognition by recall-a new paradigm for object recognition

Abstract: Recognition is a major capability of human beings and animals. In the discipline of pattern recognition, research has been carried out extensively on recognition by classification. Most of the time, a human performs recognition tasks by recall. The paper describes the framework of recognition by recall. The definitions and approaches are described and preliminary results presented.