Sketch recognition

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

Gradient feature matching for in-plane rotation invariant face sketch recognition

Abstract: Automatic recognition of face sketches is a challenging and interesting problem. An artist drawn sketch is compared against a mugshot database to identify criminals. It is a very cumbersome task to manually compare images. This necessitates a pattern recognition system to perform the comparisons. Existing methods fall into two main categories - those that allow recognition across modalities and methods that require a sketch/photo symthesis step and then copare in some modality. The methods that require synthesis require a lot of computing power since it involves high time and space complexity. Our method allows recognition across modalities. It uses the edge feature of a face sketch and face photo image to create a feature string called 'edge-string' which is a polar coordinate representation of the edge image. To generate a polar coordinate representation, we need the reference point and reference line. Using the center point of the edge image as the reference point and using a horizontal line as the reference line is the simplest solution. But, it cannot handle in-plane rotations. For this reason, we propose an approach for finding the reference line and the centroid point. The edge-strings of the face photo and face sketch are then compared using the Smith-Waterman algorithm for local string alignments. The face photo that gave the highest similarity score is the photo that matches the test face sketch input. The results on CUHK (Chinese University of Hong Kong) student dataset show the effectiveness of the proposed approach in face sketch recognition.

A Sketch Recognition Scheme for Primary Geometry Education

Abstract: Super Sketchpad(SSP) is a domestic software of dynamic mapping, providing powerful and rich functionalities for teaching and learning of geometry discipline in primary shools. Allusion to subject characteristics, this paper presents SPUI, a scheme for developing pen-based user interface. SPUI provides a more natural input interface for SSP. The SPUI gives a detailed description to the system architecture of pen-based user interface, expatiates upon all the component modules and mutual relationship of the system architecture. To demonstrate SPUI's validity, we introduce the usage at last.

Techniques for generating dynamic illustrations using principles of animation

Abstract: An animation engine is configured to apply motion amplifiers to sketches received from an end-user in order to create exaggerated, cartoon-style animation. The animation engine receives a sketch input from the end-user as well as a selection of one or more motion amplifiers. The animation engine also receives one or more control sketches that indicate how the selected motion amplifiers are applied to the sketch input. The animation engine projects the sketch input onto a sketch grid to create a sketch element, and then animates the sketch element by deforming the underlying sketch grid based on the control sketches. The animation engine then interpolates the sketch input, based on the deformations of the sketch grid, to animate the sketch. In this manner, the animation engine exposes an intuitive set of tools that allows end-users to easily apply the well-known Principles of Animation.

Gesture recognition for a partner robot based on computational intelligence

Abstract: Recently, various types of human-friendly robot have been developed. Such robots should perform voice recognition, gesture recognition, and others. This paper discusses the learning capability of a human gesture recognition method based on computational intelligence. The proposed method is composed of image processing for human face and hand detection based on a steady-state genetic algorithm, an extraction method for human hand motion based on a fuzzy spiking neural network, and an unsupervised classification method for human hand motion based on a self-organizing map. We show several experimental results and discuss their effectiveness.

Spelled sentence recognition using radon transform

Abstract: Various sign languages are used in India, but in schools for deaf, American Sign Language (ASL) is taught. So, the work is based on ASL. Sign recognition application is the development of more effective and friendly interfaces for human-machine interaction. It can provide an opportunity for a mute person to communicate with normal people without the need of an interpreter. We propose a novel system for recognition of spelled sentences from a video, based on radon transform. An algorithm is used to separate out key frames, which contain correct gestures from a video sequence. Segmentation is applied on key frames to separate out hand from complex and nonuniform background. Features are extracted by radon transform and gesture is recognized.