Image Retrieval Scheme Using Quantized Bins of Color Image Components and Adaptive Tetrolet Transform

For effective copyright protection of digital images, this paper proposes a zero-watermarking algorithm based on local image feature information. The feature matrix of the algorithm is derived from the keypoint set determined by the Speeded-Up Robust Features (SURF) algorithm, and it calculates both the gradient feature descriptors and the vortex-like texture feature (VTF) descriptors of the keypoint set. Unlike traditional texture feature descriptors, the vortex-like texture feature descriptors proposed in this paper contain richer information and exhibit better stability. The advantage of this algorithm lies in its ability to calculate the keypoints of the digital image and provide a stable vector description of the local features of these keypoints, thereby reducing the amount of erroneous information introduced during attacks. Analysis of experimental data shows that the algorithm has good effectiveness, distinguishability, security, and robustness.

Bag of Features (BoF) has been successfully exploited in content-based image retrieval for several years. Due to its performance and popularity, several extensions have been proposed that involve feature description, dictionary building, feature encoding and post-query process, etc. This paper proposes a dynamically weighting scheme for BoF-based image retrieval based on feedback. It involves two contributions: (i) analyzing the statistical distribution characteristic of similar BoF representations and (ii) computing weights dynamically based on the feedback obtained from different initial query results. We quantitatively evaluate the proposed method on two different databases. Experiments confirm that the proposed weighting scheme has better performance than the baseline of BoF-based image retrieval systems. Meanwhile, the results demonstrate the effectiveness of the weighting scheme in terms of the precision of top-N returned images.

Since low-light-level images are generally grayscale images that lack color information, it is necessary to colorize these images to enhance human vision for night vision scene. In this paper, a low-light-level image colorization method is proposed based on Laws’ texture feature descriptor. Laws’ filter can analyze the texture features of the image, which are the pointers we used to find the corresponding color information for low-light-level gray images from the reference color image. The experimental results demonstrate that our colorization method can make night vision images have colors closer to natural perception and help observers better understand night vision scenes.

Animal biometrics based recognition systems are gradually gaining more proliferation due to their diversity of application and uses. The recognition system is applied for representation, recognition of generic visual features, and classification of different species based on their phenotype appearances, the morphological image pattern, and biometric characteristics. The muzzle point image pattern is a primary animal biometric characteristic for the recognition of individual cattle. It is similar to the identification of minutiae points in human fingerprints. This study presents an automatic recognition algorithm of muzzle point image pattern of cattle for the identification of individual cattle, verification of false insurance claims, registration, and traceability process. The proposed recognition algorithm uses the texture feature descriptors, such as speeded up robust features and local binary pattern for the extraction of features from the muzzle point images at different smoothed levels of Gaussian pyramid. The feature descriptors acquired at each Gaussian smoothed level are combined using fusion weighted sum‐rule method. With a muzzle point image pattern database of 500 cattle, the proposed algorithm yields the desired level of 93.87% identification accuracy. The comparative analysis of experimental results for proposed work and appearance‐based face recognition algorithms has been done at each level.

In this paper, an image retrieval scheme has been proposed based on block level hybrid features. The block level salient feature are extracted in two parts: first level features are formed after the application of DCT and second level features are obtained after the processing of SVD. In the first level feature, salient components are computed from image blocks based on DCT transformation, which results into DC and AC coefficients. Here, the DC component is considered as the first level feature and the AC components are processed further to get the second level feature. Now, to extract second level feature, SVD is applied over the AC components which results into singular, left singular and right singular matrices. Based on the values of left and right singular matrices, some statistical parameters are computed which serve as the second level feature for the proposed scheme. To highlight the importance of extracted feature a weight factor is assigned to both first and second level features. However, more weight is given to the significant feature i.e the first level feature than the second level feature. Also, the feature extraction process is carried out separately for all the three planes of a color image, which in return gives more detailed feature for the proposed scheme. For the retrieval mechanism, similarity is measured by utilizing five existing distance measure schemes and the results are thoroughly analyzed to check the retrieval efficiency of the proposed scheme. Due to the variable weight factor, experimental results shows decent retrieval performance and the work is comparable to the existing works in image retrieval domain.

Color, texture and shape are three basic visual features in content-based image retrieval. Descriptors based on only one of them could just express parts of characteristics of images. This paper proposes a method that comprehensively utilizes domain color descriptor, edge histogram descriptor and shape feature descriptor in MPEG-7 standards, and evaluates the result according to the evaluation standards provided by MPEG-7. The experiment result shows that the method combining three features does more in line with the requirements of human visual experience, and obtains better retrieval result.

Images uploaded to media sharing websites are usually associated with a set of user-provided tags, which makes it easy to retrieve images of interest by treating the tags as index terms. However, the existing methods for tag-based image retrieval usually return irrelevant images or low-quality images. It has been argued that relevance and quality are the two most important measures for users to evaluate the performance of an image retrieval system. Therefore, in this paper, we propose an image retrieval scheme which considers the relevance and quality of an image simultaneously. Firstly, a relevance-based algorithm is utilized to rank each image in the database according to its relevance of an input query tag by taking into account both the visual similarity of image content and the semantic consistency of query tag. Then, the information of image quality score is added to refine the relevance score of each candidate image in the ranking list. Experimental results on NUS-WIDE image database and Corel image database demonstrate the effectiveness of the proposed scheme.

Cascade of descriptors to detect and track objects across any network of cameras

Lutetia surface reconstruction and uncertainty analysis

Novel local feature extraction for age invariant face recognition

Breast cancer has an important incidence in women worldwide. Early diagnosis of this illness plays a key role in decreasing its mortality and improves its prognosis. Currently, mammography is considered as the standard examination for detection of breast cancer. However, the identification of breast abnormalities and the classification of masses on mammographic images are not trivial tasks for dense breasts, and is a challenge for artificial intelligence and pattern recognition. This work presents preliminary results of automatic classification of mammographies by texture characterization based mainly on the Haralick's descriptors. We implement an artificial neural network (ANN) for classification in three classes: normal, benign and cancer using leave one out technique. The set of images for training and testing the ANN, are taken from the Digital Database for Screening Mammography (DDSM). Results show that the percentage of correct classification occurs in average for 84.72% of the data set.

Local tri-directional patterns: A new texture feature descriptor for image retrieval

The traditional privacy-preserving image retrieval schemes not only bring large computational and communication overhead but also cannot well protect the image and query privacy in multi-user scenarios. To solve the above problems, we first propose a basic privacy-preserving content-based image retrieval (CBIR) framework which significantly reduces storage and communication overhead compared with the previous works. Furthermore, we design a new efficient key conversion protocol to support unshared key multi-owner multi-user image retrieval without losing search precision. Moreover, our framework supports unbounded attributes and can trace malicious users according to leaked secret keys, which significantly improve the usability of multi-source data sharing. Strict security analysis shows that the user privacy and outsourced data security can be guaranteed during the image retrieval process, and the performance analysis using real-world dataset shows that the proposed image retrieval framework is efficient and feasible for practical applications.

Co-occurrence of adjacent sparse local ternary patterns: A feature descriptor for texture and face image retrieval

Typical applications involving image retrieval processes demand a great amount of computation. The visual content of the images is extracted and represented by means of descriptor vectors of multidimensional characteristics. The image retrieval process consists of two tasks: (1) generation of database and indexing; and (2) the search process. The first task involves the construction of descriptor vectors. Then, an index is built upon the database to speed the search process. The second requires calculating a descriptor vector for the query image and computes the similarity search with the ones stored in the index. In this context, it is relevant to devise new algorithms and different parallel platforms that can reduce execution times. In particular, this work focuses on platforms with FPGAs based SoCs to present and evaluate a two stage system where the index is constructed off-line and the similarity search is executed on-line. Results show that the FPGA is 73% faster than a 2 Quad CPU to compute the descriptor vector of an image when using the Color Layout Descriptor of MPEG-7.