International Journal of Image and Graphics

Image enhancement and segmentation are the two imperative steps while processing digital images. The goal of enhancement is to improve the quality of images so as to nullify the effect of poor illumination conditions during image acquisition. Afterwards, segmentation is performed to extract region of interest (ROI) from the background details of the image. There is a vast literature available for both the techniques. Therefore, this paper is intended to summarize the basic as well as advanced enhancement and segmentation techniques under a single heading; to provide an insight for future researches in the field of pattern recognition.

Computer generated images are assumed to be a key part in each person’s life in this era of information technology, where individuals effectively inhabit the advertisements, magazines, websites, televisions and many more. At the point when digital images played their role, the event of violations in terms of misrepresentation of information, use of their wrong doings winds up and also becomes easier with the help of image editing application programs. To be legitimate, if anyone does wrong anything then the proposed method can be used for a correct identification of the forgery and the imitations in the digital images. In existing techniques, researchers have suggested most well-known types of digital photographic manipulations based on source, meta-data, image copying, splicing and many more. The proposed approach is inspired by physics-based techniques and requires less human involvement. The presented approach works for images having any type of objects present in the scene, i.e. not only limited to human faces and selection of same intensity regions of the image. By assessing the lighting parameters, the proposed technique identifies the manipulated object and returns angle of incidence w.r.t light source direction. The demonstrated result produces forgery recognition rate of 92% on an image dataset comprising of various types of manipulated images.

In the current digital age, the piracy of digital media content has become rampant. Illegal distribution of movies and video clips on a global scale causes a significant loss to the media industry. To prevent such theft and distribution of content, we use a watermarking technique for videos where copyright information is hidden inside the original video in the form of a watermark video. Using a video as the watermark facilitates the user in hiding a large amount of information. The watermarking scheme used in this paper is semi-fragile, such that tampering of videos can be detected with relative ease. To improve the robustness of the watermark, we embed the watermark in frequency domain, where we use DWT+DCT+SVD to embed the watermark. The original video and watermark video are transformed by using the DWT and DCT sequentially, then the singular values of the watermark with some embedding strength are added to the singular values of the original video thus obtaining a watermarked video. Some detection tools which are available today cannot detect the watermark video inside the original video. This method equalizes the frames of the watermark and original video to reduce time consumed as well as complexity. The effects of various attacks on the watermarked video have been analyzed using the calculated PSNR values.

Dichromats lack one of the three cone cells, which detects red, green, and blue lights. For example, red-green color blinds cannot distinguish the color between red, yellow, and green. In order to extend the ability of dichromats to recognize the color difference, we proposed a method to expand the color difference when observed by dichromats. We have defined a hue variable for dichromats and implemented to our algorithm. We applied the histogram equalization to the hue of dichromats in order to enlarge the color difference recognized by dichromats. We have applied our method to RGB color image, and shown its performance at the experimental section.

Although the low-dose CT (LDCT) technique can reduce the radiation damage to patients, it will be highly detrimental to the reconstructed image quality. The normal-dose scan assisted algorithms have shown their potential in improving LDCT image quality by using a registered previously scanned normal-dose CT (NDCT) reference to regularize the corresponding LDCT target. The major drawback of such methods is the requirement of a previous patient-specific NDCT scan, which limits their clinical application. To address these problems, this paper proposed adaptive prior feature matching method for better restoration of the LDCT image. The innovation lies in construction of offline texture feature database and online adaptive prior feature matching integrated with the NLM regularization. Specifically, the prior features were extracted by the gray level co-occurrence matrix (GLCM) from regions of interest (ROIs) in existing NDCT scans of population patients. For online adaptive prior feature matching, ROIs with their texture features being similar to those of the current noisy target ROI are selected from the database as the references for the NLM regularization. The effectiveness of the proposed algorithm is validated by clinical lung cancer studies, the gain over traditional methods is noticeable in terms of both noise suppression and textures preservation.

Two novel methods for fully unsupervised human action retrieval using 3D mesh sequences are presented. The first achieves high accuracy but is suitable for sequences consisting of clean meshes, such as artificial sequences or highly post-processed real sequences, while the second one is robust and suitable for noisy meshes, such as those that often result from unprocessed scanning or 3D surface reconstruction errors. The first method uses a spatio-temporal descriptor based on the trajectories of 6 salient points of the human body (i.e. the centroid, the top of the head and the ends of the two upper and two lower limbs) from which a set of kinematic features are extracted. The resulting features are transformed using the wavelet transformation in different scales and a set of statistics are used to obtain the descriptor. An important characteristic of this descriptor is that its length is constant independent of the number of frames in the sequence. The second descriptor consists of two complementary sub-descriptors, one based on the trajectory of the centroid of the human body across frames and the other based on the Hybrid static shape descriptor adapted for mesh sequences. The robustness of the second descriptor derives from the robustness involved in extracting the centroid and the Hybrid sub-descriptors. Performance figures on publicly available real and artificial datasets demonstrate our accuracy and robustness claims and in most cases the results outperform the state-of-the-art.