Sketch recognition

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

Optimizing one-shot recognition with micro-set learning

Abstract: For object category recognition to scale beyond a small number of classes, it is important that algorithms be able to learn from a small amount of labeled data per additional class One-shot recognition aims to apply the knowledge gained from a set of categories with plentiful data to categories for which only a single exemplar is available for each As with earlier efforts motivated by transfer learning, we seek an internal representation for the domain that generalizes across classes However, in contrast to existing work, we formulate the problem in a fundamentally new manner by optimizing the internal representation for the one-shot task using the notion of micro-sets A micro-set is a sample of data that contains only a single instance of each category, sampled from the pool of available data, which serves as a mechanism to force the learned representation to explicitly address the variability and noise inherent in the one-shot recognition task We optimize our learned domain features so that they minimize an expected loss over micro-sets drawn from the training set and show that these features generalize effectively to previously unseen categories We detail a discriminative approach for optimizing one-shot recognition using micro-sets and present experiments on the Animals with Attributes and Caltech-101 datasets that demonstrate the benefits of our formulation

Modeling Flowchart Structure Recognition as a Max-Sum Problem

Abstract: This work deals with the on-line recognition of hand-drawn graphical sketches with structure. We present a novel approach, in which the search for a suitable interpretation of the input is formulated as a combinatorial optimization task - the max-sum problem. The recognition pipeline consists of two main stages. First, groups of strokes possibly representing symbols of a sketch (symbol candidates) are segmented and relations between them are detected. Second, a combination of symbol candidates best fitting the input is chosen by solving the optimization problem. We focused on flowchart recognition. Training and testing of our method was done on a freely available benchmark database. We correctly segmented and recognized 82.7% of the symbols having 31.5% of the diagrams recognized without any error. It indicates that our approach has promising potential and can compete with the state-of-the-art methods.

Translation and scale-invariant gesture recognition in complex scenes

Abstract: Gestures are a natural means of communication between humans, and also a natural modality for human-computer interaction. Automatic recognition of gestures using computer vision is an important task in many real-world applications, such as sign language recognition, computer games control, virtual reality, intelligent homes, and assistive environments. In order for a gesture recognition system to be robust and deployable in non-laboratory settings, the system needs to be able to operate in complex scenes, with complicated backgrounds and multiple moving and skin-colored objects. In this paper we propose an approach for improving gesture recognition performance in such complex environments. The key idea is to integrate a face detection module into the gesture recognition system, and use the face location and size to make gesture recognition invariant to scale and translation. Our experiments demonstrate the significant advantages of the proposed method over alternative computer vision methods for gesture recognition.

Real Time Hand Gesture Recognition for Human Computer Interaction

Abstract: Most of the human computer interaction interfaces that are designed today require explicit instructions from the user inthe form of keyboard taps or mouse clicks. As the complexity of these devices increase, the sheer amount of such instructions can easily disrupt, distract and overwhelm users. A novel method to recognize hand gestures for human computer interaction, using computer vision and image processing techniques, is proposed in this paper. The proposed method can successfully replace such devices (e.g. keyboard or mouse) needed for interacting with a personal computer. The method uses a commercial depth + rgb camera called Senz3D, which is cheap and easy to buy as compared to other depth cameras. The proposed method works by analyzing 3D data in real time and uses a set of classification rules to classify the number of convexity defects into gesture classes. This results in real time performance and negates the requirement of any training data. The proposed method achieves commendable performance with very low processor utilization.

Out of many, one: reliable results from unreliable recognition

Abstract: Recognition technologies such as speech recognition and optical recognition are still, by themselves, not reliable enough for many practical uses in user interfaces. However, by combining input from several sources, each of which may be unreliable by itself, and with knowledge of a specific task and context that the user is engaged in, we might achieve enough recognition to provide useful results. We describe a preliminary experiment to assist the user in giving directions for urban navigation by combining partial results from unreliable speech recognition and unreliable visual recognition.