Sketch recognition

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

A Testing Method and Cognitive Model of Human Diagram Understanding for Automating Design Sketch Recognition

Abstract: Sketches, whether hand-drawn or computer generated, are a natural and integral part of the design process. Despite this fact, modern day computational design tools are ill-equipped to take full advantage of sketching input. The computational challenges of recognizing sketches are easily overcome by human visual recognition and much insight stands to be gained by emulating human cognitive processes. Creating robust, automated tools that overcome the ambiguity of sketching input would allow for advances not only in the practice of engineering design, but in the education of design itself. One first step toward the development of a robust sketching tool is to determine how humans interpret mechanical engineering diagrams. This paper presents two contributions toward the goal of an automated diagram understanding system. First, a method is presented to gain insight into human diagram recognition using techniques analogous to peripheral vision and human attention. Following this, a cognitive model of human diagram understanding is presented from which to further develop computational design tools. With this work, researchers should be able to (1) improve understanding of human diagram recognition and (2) use our model to emulate human diagram recognition in future computational design tools.Copyright © 2009 by ASME

A words-of-interest model of sketch representation for image retrieval

Abstract: In this paper we propose a method for sketch-based image retrieval. Sketch is a magical medium which is capable of conveying semantic messages for user. It’s in accordance with user’s cognitive psychology to retrieve images with sketch. In order to narrow down the semantic gap between the user and the images in database, we preprocess all the images into sketches by the coherent line drawing algorithm. During the process of sketches extraction, saliency maps are used to filter out the redundant background information, while preserve the important semantic information. We use a variant of Words-of-Interest model to retrieve relevant images for the user according to the query. Words-of-Interest (WoI) model is based on Bag-ofvisual Words (BoW) model, which has been proven successfully for information retrieval. Bag-of-Words ignores the spatial relationships among visual words, which are important for sketch representation. Our method takes advantage of the spatial information of the query to select words of interest. Experimental results demonstrate that our sketch-based retrieval method achieves a good tradeoff between retrieval accuracy and semantic representation of users’ query.

An unsupervised method for face photo-sketch synthesis and recognition

Abstract: Face recognition is considered one of the most essential applications of Biometrics for personal identification. Face sketch recognition is a special case of face recognition, and it is very important for forensic applications. In this paper, we propose an unsupervised method for face photo-sketch recognition by synthesizing a pseudo-sketch from a single photo. The proposed method is the first unsupervised method that deals with face sketch recognition. The proposed photo-sketch synthesis step consists of two main steps, namely: edge detection and hair detection, which are applied on the grayscale image of the photo image. In the recognition step, the artist sketch is compared with the generated pseudo-sketch. PCA and LDA are used to extract features from the sketch images. The k-nearest neighbor classifier with Euclidean distance is used in the classification step. We use the CUHK database to test the performance of the proposed Method. Results for the synthesized sketches are compared with state-of-the-art methods, e.g., Local Linear Embedding (LLE) and Eigen transformation. The experimental results show that the proposed method generates a clear synthesis sketch and it defines persons more accurate than other methods. Moreover, in the recognition step, the proposed method achieves a recognition rate at the 1-nearest neighbor (rank1: first-match) range from 82% with PCA to 94% with LDA. The highest recognition rate is obtained at the 5-nearest neighbor (rank 5) is 98% that is better than some of the state-of-the-art methods.

A sketch recognition method and an application of the method in commodity retrieval

Abstract: The invention discloses a sketch recognition method, which comprises the following steps of S1, obtaining pictures to be processed; S2, segmenting the collected picture into parts with semantic information to obtain a part diagram of the sketch; S3, obtaining the label of the component through identifying the component diagram by using the depth learning network model; S4, associating the semanticinformation of the component with the semantic information of the object to which the component belongs; S5, outputting the label of the object to which the part belongs obtained through the semantictree. The application of the method in commodity retrieval is characterizd by comprising the following steps of 1) obtaining picture information; 2) using a retrieval system to utilize the sketch recognition method to obtain the label of the article that the user wants to find according to the picture; 3) recommending the corresponding commodity for the user according to the identified label. Themethod and the application of the invention improve the correct rate of the identification of the complete sketch, save the time for the user to select the commodity, and enhance the user experience.