International Journal of Image and Graphics

Fog is a natural phenomenon that affects scene visibility, it reduces the contrast of the image and causes color-fade. While various works in the literature have addressed this issue, a fast effective model is still lacking. In this paper, a single image fog removal based on Geometric Mean Histogram Equalization (GMHE) is proposed. In particular, the proposed method is composed of three steps. The primary step is to adaptively tune the performance of GMHE according to the properties of the color histogram of the foggy image. The obtained result then enters two levels of chromaticity enhancement using the Hue Saturation Value (HSV) and rotors color transformations, respectively. Extensive experiments demonstrate that the proposed method attains high performance compared to the state-of-the-art methods in terms of quality and execution time. The evaluation is performed qualitatively by visual assessment, and quantitatively using a set of full reference and no-reference-based measures. As well, we suggest an assessment criterion to combine the results of the standard measures in a single score to facilitate the comparisons between the different fog removal methods.

Securing the confidentiality of patient information using the image steganography process has gained more attention in the research community. However, embedding the patient information is a major task in the steganography process due to the complexity in identifying the pixel features. Thus, an effective Crow Search Algorithm-based deep belief network (CSA-DBN) is proposed for embedding the information in the medical image. Initially, the appropriate pixels and the features, like pixel coverage, wavelet energy, edge information, and texture features, such as local binary pattern (LBP) and local directional pattern (LDP), are extracted from each pixel. The proposed CSA-DBN utilizes the feature vector and identifies the suitable pixels used for embedding. The patient information is embedded into the image by using the embedding strength and the DWT coefficient. Finally, the embedded information is extracted using the DWT coefficient. The analysis of the proposed CSA-DBN approach is done based on the performance metrics, such as correlation coefficient, peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) that acquired the average values as 0.9471, 24.836dB, and 0.4916 in the presence of salt and pepper noise and 0.9741, 57.832dB, and 0.9766 in the absence of noise.

In video Super Resolution (SR), the problem of cost expense concerning the attainment of enhanced spatial resolution, computational complexity and difficulties in motion blur makes video SR a complex task. Moreover, maintaining temporal consistency is crucial to achieving an efficient and robust video SR model. This paper plans to develop an intelligent SR model for video frames. Initially, the video frames in RGB format will be transformed into HSV. In general, the improvement in video frames is done in V-channel to achieve High-Resolution (HR) videos. In order to enhance the RGB pixels, the current window size is enhanced to high-dimensional window size. As a novelty, this paper intends to formulate a high-dimensional matrix with enriched pixel intensity in V-channel to produce enhanced HR video frames. Estimating the enriched pixels in the high-dimensional matrix is complex, however in this paper, it is dealt in a significant way by means of a certain process: (i) motion estimation (ii) cubic spline interpolation and deblurring or sharpening. As the main contribution, the cubic spline interpolation process is enhanced via optimization in terms of selecting the optimal resolution factor and different cubic spline parameters. For optimal tuning, this paper introduces a new modified algorithm, which is the modification of the Rider Optimization Algorithm (ROA) named Mean Fitness-ROA (MF-ROA). Once the HR image is attained, it combines the HSV and converts to RGB, which obtains the enhanced output RGB video frame. Finally, the performance of the proposed work is compared over other state-of-the-art models with respect to BRISQUE, SDME and ESSIM measures, and proves its superiority over other models.

Smartphones and tablets present data and information in color images. Due to factors such as yellowing pigmentation and miosis filter, elderly people may experience difficulties and confusion when looking at the color images on smartphones and tablets. In this paper, we propose a color enhancement method to improve the color perceived by elderly people. This method is based on the color perception of the elderly simulated using the uniform yellowing pigmentation method. The proposed method enhances the colors of the images to compensate for the effect of yellowing pigmentation and miosis filter. This is achieved by utilizing the error parameters between the original colors and colors perceived by the elderly. Implementing an adaptation matrix, the error parameters are modified and distributed back into the original colors iteratively. Experimental results showed that the proposed method improves the colors perceived by the elderly.

With the emerge of advanced technologies such as high-resolution cameras and computational power, it seems to ease to built a better dermatological diagnostic system. However, the identification of skin disease is still a challenging problem with the origination of various skin diseases. In this paper, we proposed a new fusion architecture — CBI $+$ R to support the diagnosis in multiple skin diseases. The architecture combines Content-Based Image Retrieval (CBIR) and Case-Based Reasoning (CBR) technology together to facilitate medical diagnosis. CBIR is to retrieve digital dermoscopy images from a data repository using the shape, texture and color features. Along with these features, CBR is incorporated which contains symptoms, case history and treatment plan of the disease. Experiments on a set of 1210 images yielded an accuracy of 98.2%. This was a superior retrieval and diagnosis performance in comparison with the state-of-the-art works.

Security of digital data is an important task in the present era. In this paper, we propose a new scheme of digital image encryption and decryption method based on three-dimensional (3D) Arnold cat map (ACM) and elliptic curve. In this proposed encryption method, we have applied 3D ACM on the digital color image which performs the dual encryption first, it performs the permutation and second, it performs the substitution of image pixels. After that, elliptic curve cryptography (ECC) is used to encrypt the image, for this a mapping method is proposed to convert the pixels of the image as points on the elliptic curve. Further, a mapping inverting method is proposed for decryption and then 3D inverse Arnold cat map (iACM) is applied to get the original image. The statistical and security analyses are done on various images and the experimental results show the robustness of the proposed method.

Many compression methods, lossy or lossless, were developed for 3D hyperspectral images, and various standards have emerged and applied to these amounts of data in order to achieve the best rate-distortion performance. However, high-dimensional data volume of hyperspectal images is problematic for compression and decompression time. Nowadays, fast compression and especially fast decompression algorithms are of primary importance in image data applications. In this case, we present a lossy hyperspectral image compression based on supervised multimodal scheme in order to improve the compression results. The supervised multimodal method is used to reduce the amount of data before their compression with the 3D-SPIHT encoder based on 3D wavelet transform. The performance of the Supervised Multimodal Compression (SMC-3D-SPIHT encoder) has been evaluated on AVIRIS hyperspectral images. Experimental results indicate that the proposed algorithm provides very promising performance at low bit-rates while reducing the encoding/decoding time.

High resolution infrared (IR) images are often required in military and industrial applications. Due to the limited properties of IR imaging sensors and camera lens, IR images exhibit poor spatial resolution with a blur phenomenon in the edge regions. In this correspondence, we develop a new super-resolution (SR)-IR image reconstruction method using the residual learning network in the wavelet domain (WRESNET) and optimized phase stretch transform (PST). Our algorithm first transforms the input low resolution (LR)-IR image into its low-frequency and high-frequency subbands using the discrete wavelet decomposition. Subsequently, we introduce the optimized PST to operate on the LR-IR image and extract the intrinsic edge structure. The PST behaves differently at low-frequency and high-frequency regions, thus capturing the intensity variations for edge detection. We incorporate the PST extracted edge map in the wavelet subbands to preserve the intrinsic structure of images. The resultant subbands are further refined based on the missing residuals obtained using the WRESNET. The proposed method is validated through quantitative and qualitative evaluations against the conventional and state-of-art SR methods. Results reveal that the proposed method outperforms the existing methods.

A topographic sheet hosts various morphological features that effectively describe the terrain. This multi-faced information content not only elevates human perception but also provides ample direction for research initiatives. Out of all possible attributes based on utility, contours have wide set of application. A contour is characterized by its coordinate system and most importantly, its elevation detail. Upon, successful attainment of these two attributes, creating a fully automatic 3D projection system may be achieved with relative ease. In contrast to the traditional manual approach, this research initiative puts forward a novel mechanism for automatically localizing contour and its attributes including coordinate pattern and elevation value in a referenced map. To accomplish the aforementioned objectives, the proposed mechanism relies on various image processing techniques based on morphological operations. Further, the extracted details can be used to project the contours in a 3D space. This projection is also called Digital Elevation Model (DEM). DEM is crucial for various applications such as Terrain Modeling, Hydrological Modeling, Path Optimization, to name a few. Automatically and accurately created DEM from topographic sheet could contribute a lot in many Geographical Information System (GIS) applications. This paper focuses mainly on elevation value localization associated with specific contour.

In this paper, the issue of classifying mammogram abnormalities using images from an mammogram image analysis society (MIAS) database is discussed. We compare a feature extractor based on Legendre moments (LMs) with six other feature extractors. To determine the best feature extractor, the performance of each was compared in terms of classification accuracy rate and extraction time using a $k$-nearest neighbors ($k$-NN) classifier. This study shows that feature extraction using LMs performed best with an accuracy rate over 84% and requiring relatively little time for feature extraction, on average only 1s.