Sketch recognition

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

A robust approach for offline English character recognition

Abstract: Recognition rate of offline handwritten English character is still bounded due to large variation of shape, slants, and scales in hand writings. A sophisticated hand written character recognition system requires a better feature extraction technique that would take care of such variation of hand writing. In this paper, we propose a recognition model based on Artificial Neural Network (ANN) supported by novel feature extraction technique. Hand written data has continued to persist as a means of recording information in day-to-day life with the introduction of latest technologies. The constant development of computer tools lead to the requirement of easier interface between human and computers. Recognition of handwritten characters by computers is complicated task as compared to typed character. The proposed system is been implemented using MATLAB successfully. The ANN accepts the input as a scanned image. This input undergoes a sequence of pre-processing steps; binarization and normalization. Then features are extracted and matched from the stored data in the database. A data-base of 2600 samples is collected from 100 writers for each character. 1041 samples have been used to train the neural network and the rest are used to test recognition model. Using our proposed recognition system we have achieved a good average recognition rate of about 86.74 percent with minimum training time.

Face sketch recognition: an application of Z-numbers

Abstract: To simulate the capability of human decision making with rationality on a machine is a quite difficult task. In the seminal line the automation of sketching of face involves computation of words and propositions based on human perceptions. It is this challenge that motivated us to apply the concept of ‘Sketching With Words’ or SWW. Moreover, the computerization of sketching of face is augmented by the involvement of uncertainty, in perception of human, e.g. ‘I am not quite sure, nose of criminal was fairly small’. A perception based natural language statements may be represented by a set of tuples. Simple examples of Z-valuations are: (he has small eyes, closed to 2.8 cm, very likely), (forehead of criminal, small, not sure), (his nose, about 2 in., quite sure). Since ‘Z-numbers’ provides a foundation for a theory that can simulate a wide variety of rational decision made by humans, without any measurements and computations and might be made by machines. Hence, ‘Z-numbers’ are used as a tool of automation of such type of task, where the decision making is influenced by perception, experience, and mental status of human being. Various geometric objects based on fuzzy geometry are used for drawing different parts of face. These fuzzy objects are drawn by using SWW technique. Since computation of SWW with Z-numbers may provide ability to build model of real life. Hence these two concepts are used in proposed work to draw the sketch of facial features of miscreant on the basis of perceptions of eyewitness.

Image-based gesture recognition with support vector machines

Abstract: Recent advances in various display and virtual technologies, coupled with an explosion in available computing power, have given rise to a number of novel human-computer interaction (HCI) modalities, among which gesture recognition is undoubtedly the most grammatically structured and complex. However, despite the abundance of novel interaction devices, the naturalness and efficiency of HCI has remained low. This is due in particular to the lack of robust sensory data interpretation techniques. To address the task of gesture recognition, this dissertation establishes novel probabilistic approaches based on support vector machines (SVM). Of special concern in this dissertation are the shapes of contact images on a multi-touch input device for both 2D and 3D. Five main topics are covered in this work. The first topic deals with the hand pose recognition problem. To perform classification of different gestures, a recognition system must attempt to leverage between class variations (semantically varying gestures), while accommodating potentially large within-class variations (different hand poses to perform certain gestures). For recognition of gestures, a sequence of hand shapes should be recognized. We present a novel shape recognition approach using Active Shape Model (ASM) based matching and SVM based classification. Firstly, a set of correspondences between the reference shape and query image are identified through ASM. Next, a dissimilarity measure is created to measure how well any correspondence in the set aligns the reference shape and candidate shape in the query image. Finally, SVM classification is employed to search through the set to find the best match from the kernel defined by the dissimilarity measure above. Results presented show better recognition results than conventional segmentation and template matching methods. In the second topic, dynamic time alignment (DTA) based SVM gesture recognition is addressed. In particular, the proposed method combines DTA and SVM by establishing a new kernel. The gesture data is first projected into a common eigenspace formed by principal component analysis (PCA) and a distance measure is derived from the DTA. By incorporating DTA in the kernel function, general classification problems with variable-sized sequential data can be handled. In the third topic, a C++ based gesture recognition application for the multi-touchpad is implemented. It uses the proposed gesture classification method along with a recursive neural networks approach to recognize definable gestures in real time, then runs an associated command. This application can further enable users with different disabilities or preferences to custom define gestures and enhance the functionality of the multi-touchpad. Fourthly, an SVM-based classification method that uses the DTW to measure the similarity score is presented. The key contribution of this approach is the extension of trajectory based approaches to handle shape information, thereby enabling the expansion of the system's gesture vocabulary. It consists of two steps: converting a given set of frames into fixed-length vectors and training an SVM from the vectorized manifolds. Using shape information not only yields discrimination among various gestures, but also enables gestures that cannot be characterized solely based on their motion information to be classified, thus boosting overall recognition scores. Finally, a computer vision based gesture command and communication system is developed. This system performs two major tasks: the first is to utilize the 3D traces of laser pointing devices as input to perform common keyboard and mouse control; the second is supplement free continuous gesture recognition, i.e., data gloves or other assistive devices are not necessary for 3D gestures recognition. As a result, the gesture can be used as a text entry system in wearable computers or mobile communication devices, though the recognition rate is lower thanthe approaches with the assistive tools. The purpose of this system is to develop new perceptual interfaces for human computer interaction based on visual input captured by computer vision systems, and to investigate how such interfaces can complement or replace traditional interfaces. Original contributions of this work span the areas of SVMs and interpretation of computer sensory inputs, such as gestures for advanced HCI. In particular, we have addressed the following important issues: (1) ASM base kernels for shape recognition. (2) DTA based sequence kernels for gesture classification. (3) Recurrent neural networks (RNN). (4) Exploration of a customizable HCI. (5) Computer vision based 3D gesture recognition algorithms and system.

Robust multi-algorithm object recognition using Machine Learning methods

Abstract: Robust object recognition is a crucial requirement for many robotic applications. We propose a method towards increasing reliability and flexibility of object recognition for robotics. This is achieved by the fusion of diverse recognition frameworks and algorithms on score level which use characteristics like shape, texture and color of the objects. Machine Learning allows for the automatic combination of the respective recognition methods' outputs instead of having to adapt their hypothesis metrics to a common basis. We show the applicability of our approach through several real-world experiments in a service robotics environment. Great importance is attached to robustness, especially in varying environments.

Symmetric Multimodal Interaction in a Dynamic Dialogue

Abstract: Two important themes in current work on interfaces are multimodal interaction and the use of dialogue. Human multimodal dialogues are symmetric, i.e., both participants communicate multimodally. We describe a proof of concept system that supports symmetric multimodal communication for speech and sketching in the domain of simple mechanical device design. We discuss three major aspects of the communication: multimodal input processing, multimodal output generation, and creating a dynamic dialogue. While previous systems have had some of these capabilities individually, their combination appears to be unique. We provide examples from our system that illustrate a variety of user inputs and system outputs. Author Keywords multimodal, dynamic dialogue, sketch recognition, sketch generation, speech