Sketch recognition

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

Face-sketch recognition using canonical correlation analysis

Abstract: Hand-drawn face sketches are frequently used in criminal investigations. In this paper, we present a novel framework for face recognition from sketches. Our framework based is on Principle Component Analysis (PCA) and Canonical Correlation Analysis (CCA). First, we apply PCA to a dataset for dimension reduction and then apply CCA for reaching maximum correlation within a dataset. This approach is tested on two different datasets including 311 photo-sketch pairs. The performance reached 99.36% recognition rate on these experiments.

3D face view generation from human drawn sketch: A review

Abstract: From last few decades, generating a 3D face model from an human drawn sketch has caught the interest of many researchers in the area of image processing and face recognition. It has various applications in 3D cartoon modelling, police investigation and verification, and in Image Processing. Many techniques are there to generate 3D models from a sketch. 3D landmark estimation, 2D landmark detection, and synthesis of texture and surface with respect to 3-D morphable model are the steps, respectively, to generate the 3D face model. 3D face modelling using these steps has a higher rate of accuracy of identification of a person from her sketch and no proper photograph. In this piece of literature, we present a review on efficient technique that can be used to generate 3D face from sketch drawn by human.

Relative depth for behavior based recognition

Abstract: The authors propose to study object recognition by considering it in the context of an agent performing it in an environment, where the agent's intentions translate into a set of behaviors. The problem becomes a problem of action from intensity functions. In accomplishing a behavior, the next step of action from the images is determined. Acquiring the information for action is a solution for a recognition task. The recognition task is agent and behavior dependent and can use the output of different visual modules. The implementation of one visual module and its use for purposive recognition are described. It is shown how to robustly extract relative depth from a stereo setup without correspondence and calibration, and how this visual module can be used under some intentions and behaviors. For recognition under navigation behavior, relative depth was used to recognize obstacles by isolating unexpected objects in close range. For grasping behavior relative depth was used to recognize the different stages in the process. >

Efficient development of user-defined image recognition systems

Abstract: Development processes for building image recognition systems are highly specialized and require expensive expert knowledge. Despite some effort in developing generic image recognition systems, use of computer vision technology is still restricted to experts. We propose a flexible image recognition system (FOREST), which requires no prior knowledge about the recognition task and allows non-expert users to build custom image recognition systems, which solve a specific recognition task defined by the user. It provides a simple-to-use graphical interface which guides users through a simple development process for building a custom recognition system. FOREST integrates a variety of feature descriptors which are combined in a classifier using a boosting approach to provide a flexible and adaptable recognition framework. The evaluation shows, that image recognition systems developed with this framework are capable of achieving high recognition rates.