Sketch recognition

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

Handwritten gesture recognition driven by the spatial context of strokes

Abstract: In this paper, we present a new approach that explicitly exploits the spatial context of strokes to drive the shape recognition. We call this recognition method "context driven recognition" (CDR). The underlying idea is that only a sub-set of all possible symbols can be recognized in a specific spatial context. The main challenge is to detect and model automatically the context areas of interest so that the recognition method can be independent of any specific information on the targeted pen-based application. The paper details the learning scheme of the CDR method and how the obtained model is used during the recognition process. The results on a real-world pen-based recognition problem show that the method can reach better performances than a classical approach by decreasing the shape recognition complexity.

Attention-Net: An Ensemble Sketch Recognition Approach using Vector Images

Abstract: – For the past few decades, machines have replaced humans in several disciplines. However, machine cognition still lags behind the human capabilities. We address the machines’ ability to recognize human drawn sketches in this work. Visual representations such as sketches have long been a medium of communication for humans. For artificially intelligent systems to effectively immerse in interactive environments, it is required that machines understand such notations. The abstract nature and varied artistic styling of these sketches make automatic recognition of drawings more challenging than other areas of image classification. In this paper, we use sketches represented as a sequence of strokes, i.e., as vector images, to effectively capture the long-term temporal dependencies in hand-drawn sketches. The proposed approach combines the self-attention capabilities of Transformers while effectively utilizing the long-term temporal dependencies through Temporal Convolution Networks (TCN) for sketch recognition. The confidence scores obtained from the two techniques are combined using triangular-norm (T-norm). Attention heat-maps are plotted to isolate the discriminating parts of a sketch that contribute to sketch classification. The extensive quantitative and qualitative evaluation confirms that the proposed network performs favorably against state-of-the-art techniques.

Enhancing hand gesture recognition using fuzzy clustering-based mixture-of-experts model

Abstract: Hand gestures have been widely applied to interface as the way of interaction between human and computers. Since a human hand can express various shapes of gestures, previous models for recognizing them cannot distinguish them accurately since they use only single model for recognition. For efficient hand gesture recognition with its enhanced performance, we propose the fuzzy c-means clustering based mixture-of-experts (FME). The proposed method uses multiple local experts obtained via fuzzy c-means clustering and decisions from them are combined with the gating network. To evaluate the performance of the proposed method, we conduct experiments including comparisons with alternative models for hand gesture recognition. As the result of experiments, the proposed model shows improved gesture recognition performance, especially performance on similar hand gesture recognition.

An Introduction to the Design of Pattern Recognition Devices

Abstract: This paper presents the answer to a problem which may have puzzled many of the readers: given a multivariate probability density function and its marginals, how does one find the other multivariate densities which have the same set of marginals? The answer is that all the multivariate densities may be found by applying a particular transformation (called the transformation) a number of times to the product of the marginals. It thus becomes possible, by hill-clim£ ing, to find the "WDrst" or the "best" multivariate density which is concomitant with a specified set of marginals. This new technique is important in connection with problems where the designer only has access to the marginals and where he wants to bound functions of the multivariate density. Fo~ illustration, the tec! nique is used to solve two hitherto unsolved problems, one in the field of electronic circuit reliability, and one in the field of pattern recognition.