Image Search Algorithm Research Articles

A non-alternating graph hashing algorithm for large-scale image search

In the era of big data, methods for improving memory and computational efficiency have become crucial for the successful deployment of technology. Hashing is one of the most effective approaches to deal with the computational limitations associated with big data. One natural way to formulate this problem is spectral hashing, which directly incorporates an affinity to learning binary codes. However, owing to the binary constraints, the optimization becomes intractable. To mitigate this challenge, different relaxation approaches have been proposed to reduce the computational load required to obtain binary codes and still attain a good solution. The problem with all existing relaxation methods involves the use of one or more additional auxiliary variables to attain high-quality binary codes while relaxing the problem. The existence of auxiliary variables leads to the coordinate descent approach, which increases the computational complexity. We argue that the introduction of these variables is unnecessary. To this end, we propose a novel relaxed formulation for spectral hashing that adds no additional variables to the problem. Furthermore, instead of solving the problem in the original space where the number of variables is equal to the data points, we solve the problem in a much smaller space and retrieve the binary codes from this solution. This technique reduces both the memory and computational complexity simultaneously. We apply two optimization techniques, namely, the projected gradient and optimization on the manifold, to obtain the solution. Using comprehensive experiments on four public datasets, we show that the proposed efficient spectral hashing (ESH) algorithm achieves a highly competitive retrieval performance compared with the state-of-the-art algorithms at low complexity.

Visual Design of Artificial Intelligence Based on the Image Search Algorithm

Visual Design of Artificial Intelligence Based on the Image Search Algorithm

Intelligent traffic analysis: A heuristic high-dimensional image search algorithm based on spatiotemporal probability for constrained environments

However, most heuristic algorithms are solely based on image features, due to the lack of diverse attributes of samples. Rather than rely on the existing datasets, this paper fully processes the original data. Firstly, the original videos were collected from several intelligent traffic surveillance cameras (monitoring nodes). Then, the three categories of objects in all videos were classified by a video image classifier. For each object in the critical class of cars, four attributes were identified, including ID, region of interest (ROI), sampling time and sampling position (position of sampling node). Next, the moving attitude (i.e. moving direction and speed) of each object was estimated through moving target tracking, and added to the preprocessed data. On this basis, a basic hyper-spherical hash search algorithm was created for the initial identification of similar objects. Furthermore, 93% of the objects were accurately identified through the recognition of license plate. Thereafter, a spatiotemporal correlation Bayesian network (STCBN) was established to predict the probability of each object to appear at a certain node in a period of time. Based on the probability, the heuristic factor was designed and used to enhance the basic hyper-spherical hash search algorithm. The enhancement improves the search performance, while reducing the environmental requirements of a single node. Therefore, the enhanced algorithm can be deployed effectively in edge computing systems. Our method was proved effective through experiment on a number of actual monitoring nodes.

Adaptive Medical Image Deep Color Perception Algorithm

The existing medical imaging technologies have little consideration on color information, thus most of medical images are gray. Classical hand-craft features-based methods have obtained unsatisfactory results in colorizing medical images. Moreover, these methods ignore the deep feature of medical images that represent pathology and color information. In this paper, we propose a novel method that iteratively colorizes grayscale medical images under preserving content in fine-tuned deep neural network. To the best of our knowledge, there is no currently work that attempts to colorize the medical image by using deep neural network. Specifically, we propose Y-loss which is defined as nonlinear combination of $\ell _{1}$ and $\ell _{2}$ norm to preserve content invariance between target and colorized medical image. Then, adaptive reference image search algorithm is introduced to code reference and target medical image with D-hash and search reference image in hash code automatically, which free the manual selection of the reference image. Extensive experiment results show that the proposed method can generate higher quality colored medical image than recent state-of-the-art methods, and can be approved by the doctor. The objective evaluation (PSNR and SSIM) outperform an average increment 24% and 47% than baseline method, respectively. Our code is available at: https://github.com/Tongshiyue/Adaptive-medical-image-deep-color-perception-algorithm .

Enhanced image similarity analysis system in digital pathology

In digital pathology, image similarity algorithms are used to find cancer in tissue cells from medical images. However, it is very difficult to apply image similarity algorithms used in general purpose system. Because in the medical field, accuracy and reliability must be perfect when looking for cancer cells by using image similarity techniques to pathology images. To cope with this problem, this paper proposes an efficient similar image search algorithm for digital pathology by applying leveling and tiling scheme on OpenSlide format. Furthermore, we apply image sync method to extract feature key points during image similarity processing. In the experiment, to prove the efficiency of the proposed system, we conduct several experiments including algorithm performance, algorithm accuracy and computation time. The experiments result shows that the proposed system efficiently retrieves similar cell images from pathology images.

MapReduce 기반 분산 이미지 특징점 추출을 활용한 빠르고 확장성 있는 이미지 검색 알고리즘

With mobile devices showing marked improvement in performance in the age of the Internet of Things (IoT), there is demand for rapid processing of the extensive amount of multimedia big data. However, because research on image searching is focused mainly on increasing accuracy despite environmental changes, the development of fast processing of high-resolution multimedia data queries is slow and inefficient. Hence, we suggest a new distributed image search algorithm that ensures both high accuracy and rapid response by using feature extraction of distributed images based on MapReduce, and solves the problem of memory scalability based on BIRCH indexing. In addition, we conducted an experiment on the accuracy, processing time, and scalability of this algorithm to confirm its excellent performance.

A Development of Hybrid Drug Information System Using Image Recognition

In order to prevent drug abuse or misuse cases and avoid over-prescriptions, it is necessary for medicine taker to be provided with detailed information about the medicine. In this paper, we propose a drug information system and develop an application to provide information through drug image recognition using a smartphone. We designed a contents-based drug image search algorithm using the color, shape and imprint of drug. Our convenient application can provide users with detailed information about drugs and prevent drug misuse.

BSIFT: toward data-independent codebook for large scale image search.

Bag-of-Words (BoWs) model based on Scale Invariant Feature Transform (SIFT) has been widely used in large-scale image retrieval applications. Feature quantization by vector quantization plays a crucial role in BoW model, which generates visual words from the high- dimensional SIFT features, so as to adapt to the inverted file structure for the scalable retrieval. Traditional feature quantization approaches suffer several issues, such as necessity of visual codebook training, limited reliability, and update inefficiency. To avoid the above problems, in this paper, a novel feature quantization scheme is proposed to efficiently quantize each SIFT descriptor to a descriptive and discriminative bit-vector, which is called binary SIFT (BSIFT). Our quantizer is independent of image collections. In addition, by taking the first 32 bits out from BSIFT as code word, the generated BSIFT naturally lends itself to adapt to the classic inverted file structure for image indexing. Moreover, the quantization error is reduced by feature filtering, code word expansion, and query sensitive mask shielding. Without any explicit codebook for quantization, our approach can be readily applied in image search in some resource-limited scenarios. We evaluate the proposed algorithm for large scale image search on two public image data sets. Experimental results demonstrate the index efficiency and retrieval accuracy of our approach.

Content Based Image Search Using Rough Set and Representative Graph

Until now, the search carried out in devices using the conventional, textual form of search now seems tedious, considering the advances made in human software interaction since the emergence and development in touch-screen interfaces. In the past decade finger-touch or multi-touch interfaces have completely altered the way we interact with the devices. The input method implemented in search mechanisms, use the textual form of string input method that can be extended to graphical search which would enhance the interaction of human to software and also is efficient. This Paper proposes a new content based Image search Algorithm using Rough Set and Relational Graph.

FAST IMAGE MATCHING IN HUGE DATABASE

In today’s multimedia age, images are becoming more and more common in various fields. Database is an area that has found extensive use of images in past few years. With the increased usage of image data, the need to search and matching images efficiently and accurately from a large image database or a cluster of images databases has increased. Image search has be come a popular feature in many search engines, including Google, Yahoo!, MSN, etc., majority of which use very little, if any, image information. In this study we introduced a novel algorithm for searching for image in huge database based on SVD, the proposed algorithm solved some of the other searchi ng algorithms problems, like problems of image scaling, image rotation, search time. The contribut ion of this algorithm is to retrieve the exact imag e and/or the image with different view or captured in differ ent time with fixed time regardless the database si ze, database can be indexed according to the Suggested Values extracted from SVD. The proposed algorithm gives high performance and solved many issues relat ed to other image search algorithms.

A new algorithm for product image search based on salient edge characterization

Visually assisted product image search has gained increasing popularity because of its capability to greatly improve end users' e‐commerce shopping experiences. Different from general‐purpose content‐based image retrieval (CBIR) applications, the specific goal of product image search is to retrieve and rank relevant products from a large‐scale product database to visually assist a user's online shopping experience. In this paper, we explore the problem of product image search through salient edge characterization and analysis, for which we propose a novel image search method coupled with an interactive user region‐of‐interest indication function. Given a product image, the proposed approach first extracts an edge map, based on which contour curves are further extracted. We then segment the extracted contours into fragments according to the detected contour corners. After that, a set of salient edge elements is extracted from each product image. Based on salient edge elements matching and similarity evaluation, the method derives a new pairwise image similarity estimate. Using the new image similarity, we can then retrieve product images. To evaluate the performance of our algorithm, we conducted 120 sessions of querying experiments on a data set comprised of around 13k product images collected from multiple, real‐world e‐commerce websites. We compared the performance of the proposed method with that of a bag‐of‐words method (Philbin, Chum, Isard, Sivic, & Zisserman, 2008) and a Pyramid Histogram of Orientated Gradients (PHOG) method (Bosch, Zisserman, & Munoz, 2007). Experimental results demonstrate that the proposed method improves the performance of example‐based product image retrieval.

Cross-Indexing of Binary SIFT Codes for Large-Scale Image Search

In recent years, there has been growing interest in mapping visual features into compact binary codes for applications on large-scale image collections. Encoding high-dimensional data as compact binary codes reduces the memory cost for storage. Besides, it benefits the computational efficiency since the computation of similarity can be efficiently measured by Hamming distance. In this paper, we propose a novel flexible scale invariant feature transform (SIFT) binarization (FSB) algorithm for large-scale image search. The FSB algorithm explores the magnitude patterns of SIFT descriptor. It is unsupervised and the generated binary codes are demonstrated to be dispreserving. Besides, we propose a new searching strategy to find target features based on the cross-indexing in the binary SIFT space and original SIFT space. We evaluate our approach on two publicly released data sets. The experiments on large-scale partial duplicate image retrieval system demonstrate the effectiveness and efficiency of the proposed algorithm.

Towards Codebook-Free: Scalable Cascaded Hashing for Mobile Image Search

State-of-the-art image retrieval algorithms using local invariant features mostly rely on a large visual codebook to accelerate the feature quantization and matching. This codebook typically contains millions of visual words, which not only demands for considerable resources to train offline but also consumes large amount of memory at the online retrieval stage. This is hardly affordable in resource limited scenarios such as mobile image search applications. To address this issue, we propose a codebook-free algorithm for large scale mobile image search. In our method, we first employ a novel scalable cascaded hashing scheme to ensure the recall rate of local feature matching. Afterwards, we enhance the matching precision by an efficient verification with the binary signatures of these local features. Consequently, our method achieves fast and accurate feature matching free of a huge visual codebook. Moreover, the quantization and binarizing functions in the proposed scheme are independent of small collections of training images and generalize well for diverse image datasets. Evaluated on two public datasets with a million distractor images, the proposed algorithm demonstrates competitive retrieval accuracy and scalability against four recent retrieval methods in literature.

Design and Implementation of Image Search Algorithm

Image search is becoming an urgent problem of the next generation of search engine. We firstly review the developed situation of image search engine in this paper. Then, the main difficulty and key technologies about this engine are analyzed. Next, the design method is elaborated in detail, which mainly includes image recognition, perceptual hash algorithm, system solution, image retrieval procedure as well as software module, and so on. As a result, we develop an image search engine according to above design methods and implement searching image on the Internet. The testing results finally prove the overall performance of our image search engine is excellent and achieves the desired design requirements. By using data filtering technology and perceptual hash algorithm, the search time-consumed is less than 1 second and is of high search efficiency.

A Method for Measuring Weld Bead in Grinding and Polishing Process

Getting the real-time information of spatial data, height and length of weld bead is the key point during the process of grinding and polishing large-scale part. To tackle this problem, a robot visual system is completed by building the double CCD and the laser on the mobile robot. Combining the image search algorithm with the image preprocessing algorithm in time domain, the laser single pixel feature line is obtained. The positions of each point in feature line are optimized by curve fitting so that the right spatial data and dimension are obtained. The result shows the proposed method can provides the precise information of weld bead, and the accuracy of measurement is within 0.15mm, as steady as repeatability.

Joint Optimization Toward Effective and Efficient Image Search

The bag-of-words (BoW) model has been known as an effective method for large-scale image search and indexing. Recent work shows that the performance of the model can be further improved by using the embedding method. While different variants of the BoW model and embedding method have been developed, less effort has been made to discover their underlying working mechanism. In this paper, we systematically investigate the image search performance variation with respect to a few factors of the BoW model, and study how to employ the embedding method to further improve the image search performance. Subsequently, we summarize several observations based on the experiments on descriptor matching. To validate these observations in a real image search, we propose an effective and efficient image search scheme, in which the BoW model and embedding method are jointly optimized in terms of effectiveness and efficiency by following these observations. Our comprehensive experiments demonstrate that it is beneficial to employ these observations to develop an image search algorithm, and the proposed image search scheme outperforms state-of-the art methods in both effectiveness and efficiency.

Social-oriented visual image search

Many research have been focusing on how to match the textual query with visual images and their surrounding texts or tags for Web image search. The returned results are often unsatisfactory due to their deviation from user intentions, particularly for queries with heterogeneous concepts (such as “apple”, “jaguar”) or general (non-specific) concepts (such as “landscape”, “hotel”). In this paper, we exploit social data from social media platforms to assist image search engines, aiming to improve the relevance between returned images and user intentions (i.e., social relevance). Facing the challenges of social data sparseness, the tradeoff between social relevance and visual relevance, and the complex social and visual factors, we propose a community-specific Social-Visual Ranking (SVR) algorithm to rerank the Web images returned by current image search engines. The SVR algorithm is implemented by PageRank over a hybrid image link graph, which is the combination of an image social-link graph and an image visual-link graph. By conducting extensive experiments, we demonstrated the importance of both visual factors and social factors, and the advantages of social-visual ranking algorithm for Web image search.

Comparing user experience in a news website across three devices: iPhone, iPad, and desktop

AbstractMobile devices are becoming an increasingly important access channel for news resources and services. Even though providing a mobile site for mobile device users may greatly enhance their news reading experience, many news organizations cannot afford such an additional option due to limited funding and staffing resources. Therefore, an alternative approach is to design a full website with careful consideration of both desktop users and mobile users. This study compared user experiences in a news website accessed via mobile devices (iPhone & iPad) as well as desktop computers. We aimed to discover similar and different design requirements across desktop, iPad, and iPhone users. Users across three types of devices reported to have similar perspectives on the organization schemes of news, the importance of currency of news, the need for more powerful image search functions and algorithms, and better visibility of menus/buttons. Meanwhile, differences between mobile users and desktop users have also been identified: mobile users reported requirements of making more efficient use of space on web pages, less typing, more user control and flexibility, and more sharing options via social media. Based on the findings, we provided a series of recommendations for improving the design of a full site which can meet the needs of both mobile and desktop users.

A Heuristic Image Search Algorithm for Active Shape Model Segmentation of the Caudate Nucleus and Hippocampus in Brain MR Images of Children with FASD

Magnetic Resonance Imaging provides a non-invasive means to study the neural correlates of Fetal Alcohol Spectrum Disorder (FASD) - the most common form of preventable mental retardation worldwide. One approach aims to detect brain abnormalities through an assessment of volume and shape of two sub-cortical structures, the caudate nucleus and hippocampus. We present a method for automatically segmenting these structures from high-resolution MR images captured as part of an ongoing study into the neural correlates of FASD.
 
 Our method incorporates an Active Shape Model, which is used to learn shape variation from manually segmented training data. A modified discrete Geometrically Deformable Model is used to generate point correspondence between training models. An ASM is then created from the landmark points. Experiments were conducted on the image search phase of ASM segmentation, in order to find the technique best suited to segmentation of the hippocampus and caudate nucleus. Various popular image search techniques were tested, including an edge detection method and a method based on grey profile Mahalanobis distance measurement. A novel heuristic image search method was also developed and tested. This heuristic method improves image segmentation by taking advantage of characteristics specific to the target data, such as a relatively homogeneous tissue colour in target structures.
 
 Results show that ASMs that use the heuristic image search technique produce the most accurate segmentations. An ASM constructed using this technique will enable researchers to quickly, reliably, and automatically segment test data for use in the FASD study.

Energy Efficient Content Based Image Retrieval in Sensor Networks

The presence of increased memory and computational power in imaging sensor networks attracts researchers to exploit image processing algorithms on distributed memory and computational power. In this paper, a typical perimeter is investigated with a number of sensors placed to form an image sensor network for the purpose of content based distributed image search. Image search algorithm is used to enable distributed content based image search within each sensor node. The energy model is presented to calculate energy efficiency for various cases of image search and transmission. The simulations are carried out based on consideration of continuous monitoring or event driven activity on the perimeter. The simulation setups consider distributed image processing on sensor nodes and results show that energy saving is significant if search algorithms are embedded in image sensor nodes and image processing is distributed across sensor nodes. The tradeoff between sensor life time, distributed image search and network deployed cost is also investigated.