Aun Irtaza

Embedding neural networks for semantic association in content based image retrieval

Content based image retrieval (CBIR) systems provide potential solution of retrieving semantically similar images from large image repositories against any query image. The research community are competing for more effective ways of content based image retrieval, so they can be used in serving time critical applications in scientific and industrial domains. In this paper a Neural Network based architecture for content based image retrieval is presented. To enhance the capabilities of proposed work, an efficient feature extraction method is presented which is based on the concept of in-depth texture analysis. For this wavelet packets and Eigen values of Gabor filters are used for image representation purposes. To ensure semantically correct image retrieval, a partial supervised learning scheme is introduced which is based on K-nearest neighbors of a query image, and ensures the retrieval of images in a robust way. To elaborate the effectiveness of the presented work, the proposed method is compared with several existing CBIR systems, and it is proved that the proposed method has performed better then all of the comparative systems.

Content Based Image Retrieval Using Embedded Neural Networks with Bandletized Regions

One of the major requirements of content based image retrieval (CBIR) systems is to ensure meaningful image retrieval against query images. The performance of these systems is severely degraded by the inclusion of image content which does not contain the objects of interest in an image during the image representation phase. Segmentation of the images is considered as a solution but there is no technique that can guarantee the object extraction in a robust way. Another limitation of the segmentation is that most of the image segmentation techniques are slow and their results are not reliable. To overcome these problems, a bandelet transform based image representation technique is presented in this paper, which reliably returns the information about the major objects found in an image. For image retrieval purposes, artificial neural networks (ANN) are applied and the performance of the system and achievement is evaluated on three standard data sets used in the domain of CBIR.

Categorical image retrieval through genetically optimized support vector machines (GOSVM) and hybrid texture features

Content-based image retrieval (CBIR) systems provide a potential solutions of retrieving semantically similar images from large image repositories against any query image. The research community is competing for more efficient and effective methods of content-based image retrieval, so they can be employed in serving time critical applications in scientific and industrial domains. In this paper, we have combined genetic algorithm and support vector machines to reduce the existing gap between high-level semantic content of the images and the information provided by their low-level descriptors. To maximize the performance of proposed technique, an efficient feature extraction method is introduced, which is based on the concept of in-depth texture analysis. To further enhance the capabilities of proposed method, we employed a way through which the risk of mis-associations can be avoided. To justify the effectiveness of the proposed method, we compared it against several popular CBIR techniques and show a significant improvement in terms of accuracy and stability based on Corel image gallery.

Copy-Move Forgery Detection Technique for Forensic Analysis in Digital Images

Due to the powerful image editing tools images are open to several manipulations; therefore, their authenticity is becoming questionable especially when images have influential power, for example, in a court of law, news reports, and insurance claims. Image forensic techniques determine the integrity of images by applying various high-tech mechanisms developed in the literature. In this paper, the images are analyzed for a particular type of forgery where a region of an image is copied and pasted onto the same image to create a duplication or to conceal some existing objects. To detect the copy-move forgery attack, images are first divided into overlapping square blocks and DCT components are adopted as the block representations. Due to the high dimensional nature of the feature space, Gaussian RBF kernel PCA is applied to achieve the reduced dimensional feature vector representation that also improved the efficiency during the feature matching. Extensive experiments are performed to evaluate the proposed method in comparison to state of the art. The experimental results reveal that the proposed technique precisely determines the copy-move forgery even when the images are contaminated with blurring, noise, and compression and can effectively detect multiple copy-move forgeries. Hence, the proposed technique provides a computationally efficient and reliable way of copy-move forgery detection that increases the credibility of images in evidence centered applications.

A survey on block based copy move image forgery detection techniques

In todays modern life, digital images have significant importance because they have become a leading source of information dissemination. However, the availability of image editing tools made it easier to forge the contents of a digital image; making the authenticity untrustful. Different techniques can be used to forge the digital images. Copy move forgery is the most popular and common approach where a specific part of an image is copied and pasted elsewhere in the same image to conceal unwanted part or object. In this study, we attempted to survey several passive block based copy move forgery detection techniques. A passive technique attempts to identify forgery in digital images without any prior information. A comparison between various techniques is also included.

Content based image retrieval in a web 3.0 environment

With the dramatic growth of Internet and multimedia applications, a virtually free worldwide digital distribution infrastructure has emerged. The concept of intelligent web or web 3.0 gives an opportunity to its users to share information in a way that could reach a broader audience and provide that audience with much deeper accessibility and interpretation of the information. Legacy image search systems which rely on the text annotations like keywords, and captions to retrieve images are not appropriate in web 3.0 architecture. Because these systems are unable to retrieve images which do not have this associated information. Also these systems suffers from the high cost of manual text annotations and linguistic problems as well while sharing and retrieving images. Therefore to handle these issues an image retrieval and management technique is presented in this paper which considers the actual image contents and do not rely on the associated metadata. Our content based image retrieval technique incorporates Genetic algorithms with support vector machines and user feedbacks for image retrieval purposes, and assures the effective retrieval and sharing of images by taking the users considerations into an account.

Copy–move forgery detection through stationary wavelets and local binary pattern variance for forensic analysis in digital images

The most common image tampering often for malicious purposes is to copy a region of the same image and paste to hide some other region. As both regions usually have same texture properties, therefore, this artifact is invisible for the viewers, and credibility of the image becomes questionable in proof centered applications. Hence, means are required to validate the integrity of the image and identify the tampered regions. Therefore, this study presents an efficient way of copy-move forgery detection (CMFD) through local binary pattern variance (LBPV) over the low approximation components of the stationary wavelets. CMFD technique presented in this paper is applied over the circular regions to address the possible post processing operations in a better way. The proposed technique is evaluated on CoMoFoD and Kodak lossless true color image (KLTCI) datasets in the presence of translation, flipping, blurring, rotation, scaling, color reduction, brightness change and multiple forged regions in an image. The evaluation reveals the prominence of the proposed technique compared to state of the arts. Consequently, the proposed technique can reliably be applied to detect the modified regions and the benefits can be obtained in journalism, law enforcement, judiciary, and other proof critical domains.

Stochastic Optimized Relevance Feedback Particle Swarm Optimization for Content Based Image Retrieval

One of the major challenges for the CBIR is to bridge the gap between low level features and high level semantics according to the need of the user. To overcome this gap, relevance feedback (RF) coupled with support vector machine (SVM) has been applied successfully. However, when the feedback sample is small, the performance of the SVM based RF is often poor. To improve the performance of RF, this paper has proposed a new technique, namely, PSO-SVM-RF, which combines SVM based RF with particle swarm optimization (PSO). The aims of this proposed technique are to enhance the performance of SVM based RF and also to minimize the user interaction with the system by minimizing the RF number. The PSO-SVM-RF was tested on the coral photo gallery containing 10908 images. The results obtained from the experiments showed that the proposed PSO-SVM-RF achieved 100% accuracy in 8 feedback iterations for top 10 retrievals and 80% accuracy in 6 iterations for 100 top retrievals. This implies that with PSO-SVM-RF technique high accuracy rate is achieved at a small number of iterations.

Correlated Networks for Content Based Image Retrieval

Abstract Efficient CBIR systems are based on three things, (1) how they represent the repository images in the form of signature; (2) how they measure the similarity of the database images with query image, (3) how they retrieve the semantically similar images in response of a query image. The paper is focusing on these three things. For signature development, curvelet transform, wavelet packets, and Gabor filters based signature development is introduced. For measuring the similarity, Pearson correlation is used as a distance measure; and for retrieving the semantically similar images in response of query images, Neural Network based architecture for content based image retrieval is presented. These things ensure the retrieval of images in a robust way. To elaborate the effectiveness of the presented work, the proposed method is compared with several existing CBIR systems, and it is proved that the proposed method has performed better than all comparative systems.

Fusion of local and global features for effective image extraction

Image extraction methods rely on locating interest points and describing feature vectors for these key points. These interest points provide different levels of invariance to the descriptors. The image signature can be described well by the pixel regions that surround the interest points at the local and global levels. This contribution presents a feature descriptor that combines the benefits of local interest point detection with the feature extraction strengths of a fine-tuned sliding window in combination with texture pattern analysis. This process is accomplished with an improved Moravec method using the covariance matrix of the local directional derivatives. These directional derivatives are compared with a scoring factor to identify which features are corners, edges or noise. Located interest point candidates are fetched for the sliding window algorithm to extract robust features. These locally-pointed global features are combined with monotonic invariant uniform local binary patterns that are extracted a priory as part of the proposed method. Extensive experiments and comparisons are conducted on the benchmark ImageNet, Caltech-101, Caltech-256 and Corel-100 datasets and compared with sophisticated methods and state-of-the-art descriptors. The proposed method outperforms the other methods with most of the descriptors and many image categories.