Evaluation of Near-Duplicate Image Retrieval Algorithms for the Identification of Celebrities in Web Images

2013 ◽  
Vol 765-767 ◽  
pp. 1431-1435
Author(s):  
Feng Cai Qiao ◽  
Xin Zhang ◽  
Hui Wang ◽  
Jian Ping Cao

Near-duplicate image retrieval is a classical research problem in computer vision, for which a large number of diverse approaches have been proposed. Recent studies have revealed that it can be used as an intermediate step to implement search-based celebrity identification given the existence of huge volume of user-tagged or text-surrounded celebrity images on the web. However, the effectiveness of existing near-duplicate image retrieval methods for such a task still remains unclear. To address this issue, this paper presents a comprehensive study of the existing near-duplicate image retrieval methods in a structural way. Four representatives of the existing methods, i.e. hash signature, mean SSIM, BoVW with SIFT features and ARG, are experimentally evaluated using a self-constructed dataset containing 24762 images of 15 top searched celebrities collected using 6 news search engines and the Google image search engine. The experimental results reveal that, compared with global feature based methods, local feature based ones are usually more appropriate for the task of celebrity identification in web images, as they can deal with partial duplicate and scene similar images better. In particular, BoVW with SIFT features is recommended as it provides the best trade-off between on-line speed and retrieval accuracy.

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Fengcai Qiao ◽  
Cheng Wang ◽  
Xin Zhang ◽  
Hui Wang

Near-duplicate image retrieval is a classical research problem in computer vision toward many applications such as image annotation and content-based image retrieval. On the web, near-duplication is more prevalent in queries for celebrities and historical figures which are of particular interest to the end users. Existing methods such as bag-of-visual-words (BoVW) solve this problem mainly by exploiting purely visual features. To overcome this limitation, this paper proposes a novel text-based data-driven reranking framework, which utilizes textual features and is combined with state-of-art BoVW schemes. Under this framework, the input of the retrieval procedure is still only a query image. To verify the proposed approach, a dataset of 2 million images of 1089 different celebrities together with their accompanying texts is constructed. In addition, we comprehensively analyze the different categories of near duplication observed in our constructed dataset. Experimental results on this dataset show that the proposed framework can achieve higher mean average precision (mAP) with an improvement of 21% on average in comparison with the approaches based only on visual features, while does not notably prolong the retrieval time.


2011 ◽  
Vol 11 (03) ◽  
pp. 339-353 ◽  
Author(s):  
XING-YUAN WANG ◽  
ZHI-FENG CHEN ◽  
JIAO-JIAO YUN

This paper presents an effective two-level color image retrieval method based on the RGB color model. For the purpose of effectively retrieving more similar images from the digital image databases, we divide the image into different regions and set bigger weight for the region we focus on. In addition, we set different weights for each RGB component of the color image according to the main hue of it. As a result, this scheme can enhance the retrieval accuracy that is measured in terms of the recall and precision.


Author(s):  
Mohammed Lamine Kherfi ◽  
Djemel Ziou

We present a new approach for improving image retrieval accuracy by integrating semantic concepts. First, images are represented according to different abstraction levels. At the lowest level, they are represented with visual features. At the upper level, they are represented with a set of very specific keywords. At the subsequent levels, they are represented with more general keywords. Second, visual content together with keywords are used to create a hierarchical index. A probabilistic classification approach is proposed, which allows to group similar images into the same class. Finally this index is exploited to define three retrieval mechanisms: the first is text-based, the second is content-based, and the third is a combination of both. Experiments show that our combination allows to nicely narrow the semantic gap encountered by most current image retrieval systems. Furthermore, we show that the proposed method helps reducing retrieval time and improving retrieval accuracy.


2015 ◽  
Vol 743 ◽  
pp. 503-509
Author(s):  
Q.Q. Li ◽  
C.S. Zhou ◽  
X.Q. Lv ◽  
H.Y. Yang ◽  
K. Zhang

Due to the diversity and complexity of design patent images, it is difficult to retrieve well if extracting features from images directly. A design patent image retrieval method based on Gabor filter and LBP is proposed in the paper. Firstly, doing low-pass filtering to the normalized images with Gabor filter to amplify the images’ details, then extracting image’s texture feature with LBP algorithm, calculating images’ similarity according to the distance formula after feature vectors’ internal normalization, finally return several similar images. The experimental results show that this retrieval method get better retrieval accuracy and correct rate.


Author(s):  
Shikha Bhardwaj ◽  
Gitanjali Pandove ◽  
Pawan Kumar Dahiya

Background: In order to retrieve a particular image from vast repository of images, an efficient system is required and such an eminent system is well-known by the name Content-based image retrieval (CBIR) system. Color is indeed an important attribute of an image and the proposed system consist of a hybrid color descriptor which is used for color feature extraction. Deep learning, has gained a prominent importance in the current era. So, the performance of this fusion based color descriptor is also analyzed in the presence of Deep learning classifiers. Method: This paper describes a comparative experimental analysis on various color descriptors and the best two are chosen to form an efficient color based hybrid system denoted as combined color moment-color autocorrelogram (Co-CMCAC). Then, to increase the retrieval accuracy of the hybrid system, a Cascade forward back propagation neural network (CFBPNN) is used. The classification accuracy obtained by using CFBPNN is also compared to Patternnet neural network. Results: The results of the hybrid color descriptor depict that the proposed system has superior results of the order of 95.4%, 88.2%, 84.4% and 96.05% on Corel-1K, Corel-5K, Corel-10K and Oxford flower benchmark datasets respectively as compared to many state-of-the-art related techniques. Conclusion: This paper depict an experimental and analytical analysis on different color feature descriptors namely, Color moment (CM), Color auto-correlogram (CAC), Color histogram (CH), Color coherence vector (CCV) and Dominant color descriptor (DCD). The proposed hybrid color descriptor (Co-CMCAC) is utilized for the withdrawal of color features with Cascade forward back propagation neural network (CFBPNN) is used as a classifier on four benchmark datasets namely Corel-1K, Corel-5K and Corel-10K and Oxford flower.


2018 ◽  
Vol 10 (6) ◽  
pp. 964 ◽  
Author(s):  
Zhenfeng Shao ◽  
Ke Yang ◽  
Weixun Zhou

Benchmark datasets are essential for developing and evaluating remote sensing image retrieval (RSIR) approaches. However, most of the existing datasets are single-labeled, with each image in these datasets being annotated by a single label representing the most significant semantic content of the image. This is sufficient for simple problems, such as distinguishing between a building and a beach, but multiple labels and sometimes even dense (pixel) labels are required for more complex problems, such as RSIR and semantic segmentation.We therefore extended the existing multi-labeled dataset collected for multi-label RSIR and presented a dense labeling remote sensing dataset termed "DLRSD". DLRSD contained a total of 17 classes, and the pixels of each image were assigned with 17 pre-defined labels. We used DLRSD to evaluate the performance of RSIR methods ranging from traditional handcrafted feature-based methods to deep learning-based ones. More specifically, we evaluated the performances of RSIR methods from both single-label and multi-label perspectives. These results demonstrated the advantages of multiple labels over single labels for interpreting complex remote sensing images. DLRSD provided the literature a benchmark for RSIR and other pixel-based problems such as semantic segmentation.


Today is a digital world. Due to the increase in imaging system, digital storage capacity and internetworking technology Content Based Retrieval of Images (CBIR) has become a vibrant research spot. The CBIR systems helps user to browse and retrieve similar kind of images from huge databases and World Wide Web. The Object based Image Retrieval (OBIR) Systems are the extension to the CBIR technique where it retrieves the similar images based on the object properties. So far massive amount of work has been done in this field of research. A plenty of the techniques and algorithms are published in the different papers. This paper provides brief survey on basic and recent approaches and techniques explained in different papers.


Author(s):  
Jianke Zhu

Visual odometry is an important research problem for computer vision and robotics. In general, the feature-based visual odometry methods heavily rely on the accurate correspondences between local salient points, while the direct approaches could make full use of whole image and perform dense 3D reconstruction simultaneously. However, the direct visual odometry usually suffers from the drawback of getting stuck at local optimum especially with large displacement, which may lead to the inferior results. To tackle this critical problem, we propose a novel scheme for stereo odometry in this paper, which is able to improve the convergence with more accurate pose. The key of our approach is a dual Jacobian optimization that is fused into a multi-scale pyramid scheme. Moreover, we introduce a gradient-based feature representation, which enjoys the merit of being robust to illumination changes. Furthermore, a joint direct odometry approach is proposed to incorporate the information from the last frame and previous keyframes. We have conducted the experimental evaluation on the challenging KITTI odometry benchmark, whose promising results show that the proposed algorithm is very effective for stereo visual odometry.


2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Haopeng Lei ◽  
Simin Chen ◽  
Mingwen Wang ◽  
Xiangjian He ◽  
Wenjing Jia ◽  
...  

Due to the rise of e-commerce platforms, online shopping has become a trend. However, the current mainstream retrieval methods are still limited to using text or exemplar images as input. For huge commodity databases, it remains a long-standing unsolved problem for users to find the interested products quickly. Different from the traditional text-based and exemplar-based image retrieval techniques, sketch-based image retrieval (SBIR) provides a more intuitive and natural way for users to specify their search need. Due to the large cross-domain discrepancy between the free-hand sketch and fashion images, retrieving fashion images by sketches is a significantly challenging task. In this work, we propose a new algorithm for sketch-based fashion image retrieval based on cross-domain transformation. In our approach, the sketch and photo are first transformed into the same domain. Then, the sketch domain similarity and the photo domain similarity are calculated, respectively, and fused to improve the retrieval accuracy of fashion images. Moreover, the existing fashion image datasets mostly contain photos only and rarely contain the sketch-photo pairs. Thus, we contribute a fine-grained sketch-based fashion image retrieval dataset, which includes 36,074 sketch-photo pairs. Specifically, when retrieving on our Fashion Image dataset, the accuracy of our model ranks the correct match at the top-1 which is 96.6%, 92.1%, 91.0%, and 90.5% for clothes, pants, skirts, and shoes, respectively. Extensive experiments conducted on our dataset and two fine-grained instance-level datasets, i.e., QMUL-shoes and QMUL-chairs, show that our model has achieved a better performance than other existing methods.


Sign in / Sign up

Export Citation Format

Share Document