scispace - formally typeset
Search or ask a question
Topic

Sketch recognition

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


Papers
More filters
Proceedings ArticleDOI
06 Jun 2017
TL;DR: This paper uses deep convolutional neural networks (ConvNets) to address sketch-based image retrieval (SBIR) and proposes a new architecture the quadruplet networks which enhance ConvNet features for SBIR, enabling ConvNets to extract more robust global and local features.
Abstract: Freehand sketches are a simple and powerful tool for communication. They are easily recognized across cultures and suitable for various applications. In this paper, we use deep convolutional neural networks (ConvNets) to address sketch-based image retrieval (SBIR). We first train our ConvNets on sketch and image object recognition in a large scale benchmark for SBIR (the sketchy database). We then conduct a comprehensive study of ConvNets features for SBIR, using a kNN similarity search paradigm in the ConvNet feature space. In contrast to recent SBIR works, we propose a new architecture the quadruplet networks which enhance ConvNet features for SBIR. This new architecture enables ConvNets to extract more robust global and local features. We evaluate our approach on three large scale datasets. Our quadruplet networks outperform previous state-of-the-art on two of them by a significant margin and gives competitive results on the third. Our system achieves a recall of 42.16% (at k=1) for the sketchy database (more than 5% improvement), a Kendal score of 43.28Τb on the TU-Berlin SBIR benchmark (close to 6Τb improvement) and a mean average precision (MAP) of 32.16% on Flickr15k (a category level SBIR benchmark).

41 citations

Proceedings ArticleDOI
23 Aug 2004
TL;DR: This work implemented a flower recognition system and evaluated it on 30 inexperienced subjects, finding that the accuracy of the CAVIAR system is much higher than that of the machine alone and it can be initialized with as few as one training sample per class and still achieve high accuracy.
Abstract: We introduce the concept of computer assisted visual interactive recognition (CAVIAR). In CAVIAR, a parameterized geometrical model serves as the human-computer communication channel. We implemented a flower recognition system and evaluated it on 30 inexperienced subjects. Major conclusions include: 1) the accuracy of the CAVIAR system is much higher than that of the machine alone; 2) its recognition time is much lower than that of the human alone; 3) it can be initialized with as few as one training sample per class and still achieve high accuracy; 4) it demonstrates a self-learning ability, which suggests that instead of initializing the CAVIAR system with many training samples, we can trust the system's self-learning ability.

41 citations

Book
01 Jan 2007
TL;DR: The first € price and the £ and $ price are net prices, subject to local VAT, and the €(D) includes 7% for Germany, the€(A) includes 10% for Austria.
Abstract: The first € price and the £ and $ price are net prices, subject to local VAT. Prices indicated with * include VAT for books; the €(D) includes 7% for Germany, the €(A) includes 10% for Austria. Prices indicated with ** include VAT for electronic products; 19% for Germany, 20% for Austria. All prices exclusive of carriage charges. Prices and other details are subject to change without notice. All errors and omissions excepted. H. Wechsler Reliable Face Recognition Methods

40 citations

Proceedings ArticleDOI
15 Oct 2019
TL;DR: A Triplet Classification Network (TC-Net) for iSBIR is presented which is composed of two major components: triplet Siamese network, and auxiliary classification loss which can break the limitations existed in previous works.
Abstract: Sketch has been employed as an effective communication tool to express the abstract and intuitive meaning of object. While content-based sketch recognition has been studied for several decades, the instance-level Sketch Based Image Retrieval (iSBIR) task has attracted significant research attention recently. In many previous iSBIR works -- TripletSN, and DSSA, edge maps were employed as intermediate representations in bridging the cross-domain discrepancy between photos and sketches. However, it is nontrivial to efficiently train and effectively use the edge maps in an iSBIR system. Particularly, we find that such an edge map based iSBIR system has several major limitations. First, the system has to be pre-trained on a significant amount of edge maps, either from large-scale sketch datasets, e.g., TU-Berlin~\citeeitz2012hdhso, or converted from other large-scale image datasets, e.g., ImageNet-1K\citedeng2009imagenet dataset. Second, the performance of such an iSBIR system is very sensitive to the quality of edge maps. Third and empirically, the multi-cropping strategy is essentially very important in improving the performance of previous iSBIR systems. To address these limitations, this paper advocates an end-to-end iSBIR system without using the edge maps. Specifically, we present a Triplet Classification Network (TC-Net) for iSBIR which is composed of two major components: triplet Siamese network, and auxiliary classification loss. Our TC-Net can break the limitations existed in previous works. Extensive experiments on several datasets validate the efficacy of the proposed network and system.

40 citations

Proceedings ArticleDOI
02 Jul 2007
TL;DR: An overview of face recognition research activities at the interACT Research Center is given, which includes development of a fast and robust face recognition algorithm and fully automatic face recognition systems that can be deployed for real-life smart interaction applications.
Abstract: In this paper an overview of face recognition research activities at the interACT Research Center is given. The face recognition efforts at the interACT Research Center consist of development of a fast and robust face recognition algorithm and fully automatic face recognition systems that can be deployed for real-life smart interaction applications. The face recognition algorithm is based on appearances of local facial regions that are represented with discrete cosine transform coefficients. Three fully automatic face recognition systems have been developed that are based on this algorithm. The first one is the "door monitoring system" that observes the entrance of a room and identifies the subjects while they are entering the room. The second one is the "portable face recognition system" that aims at environment-free face recognition and recognizes the user of a machine. The third system, "3D face recognition system", performs fully automatic face recognition on 3D range data.

40 citations


Network Information
Related Topics (5)
Feature (computer vision)
128.2K papers, 1.7M citations
84% related
Object detection
46.1K papers, 1.3M citations
83% related
Feature extraction
111.8K papers, 2.1M citations
82% related
Image segmentation
79.6K papers, 1.8M citations
81% related
Convolutional neural network
74.7K papers, 2M citations
80% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202326
202271
202130
202029
201946
201827