Vasif V. Nabiyev

Automatic age classification with LBP

Estimating the age exactly and then producing the younger and older images of the person is important in security systems design. In this paper local binary patterns are used to classify the age from facial images. The local binary patterns (LBP) are fundamental properties of local image texture and the occurrence histogram of these patterns is an effective texture feature for face description. In the study we classify the FERET images according to their ages with 10 years intervals. The faces are divided into small regions from which the LBP histograms are extracted and concatenated into a feature vector to be used as an efficient face descriptor. For every new face presented to the system, spatial LBP histograms are produced and used to classify the image into one of the age classes. In the classification phase, minimum distance, nearest neighbor and k-nearest neighbor classifiers are used. The experimental results have shown that system performance is 80% for age estimation.

Medical image security and EPR hiding using Shamir's secret sharing scheme

Medical applications such as telediagnosis require information exchange over insecure networks. Therefore, protection of the integrity and confidentiality of the medical images is an important issue. Another issue is to store electronic patient record (EPR) in the medical image by steganographic or watermarking techniques. Studies reported in the literature deal with some of these issues but not all of them are satisfied in a single method. A medical image is distributed among a number of clinicians in telediagnosis and each one of them has all the information about the patients medical condition. However, disclosing all the information about an important patients medical condition to each of the clinicians is a security issue. This paper proposes a (k, n) secret sharing scheme which shares medical images among a health team of n clinicians such that at least k of them must gather to reveal the medical image to diagnose. Shamirs secret sharing scheme is used to address all of these security issues in one method. The proposed method can store longer EPR strings along with better authenticity and confidentiality properties while satisfying all the requirements as shown in the results.

Secret image sharing scheme with adaptive authentication strength

Transmission of secret messages or images over the Internet using Shamirs secret sharing scheme has become popular. Some researchers use steganography with Shamirs method to hide noise like share images into natural looking cover images to improve secrecy. Stego images are authenticated against accidental or deliberate changes before recovering the secret. Authentication by a parity bit stream calculated by a keyed hash of stego images is commonly used. Researchers aim to increase the number of authentication bits to improve the authentication strength of their methods. Eslami and Ahmadabadi (2011) proposed a method with dynamic embedding strategy in 2011. They use a concatenated string of four bits, two from the current and two from previous block, to authenticate individual blocks. Even though chaining performs block based authentication, it cannot detect individual fake stego blocks and cannot authenticate the rest of the stego image blocks if it faces a changed block. This paper proposes a new secret image sharing method by selecting the number of authentication bits proportional to block size, contrary to Eslami and Ahmadabadi (2011) method which uses four bits to authenticate blocks regardless of block size. The proposed method has improved authentication for increased block size and can authenticate individual stego blocks as well. It produces good quality stego images and can still authenticate the rest of the stego image even after an altered stego block is encountered as shown in the experimental results.

A novel automatic suspicious mass regions identification using Havrda & Charvat entropy and Otsu's N thresholding

Mass detection is a very important process for breast cancer diagnosis and computer aided systems. It can be very complex when the mass is small or invisible because of dense breast tissue. Therefore, the extraction of suspicious mass region can be very challenging. This paper proposes a novel segmentation algorithm to identify mass candidate regions in mammograms. The proposed system includes three parts: breast region and pectoral muscle segmentation, image enhancement and suspicious mass regions identification. The first two parts have been examined in previous studies. In this study, we focused on suspicious mass regions identification using a combination of Havrda & Charvat entropy method and Otsus N thresholding method. An open access Mammographic Image Analysis Society (MIAS) database, which contains 59 masses, was used for the study. The proposed system obtained a 93% sensitivity rate for suspicious mass regions identification in 56 abnormal and 40 normal images.

Medical images enhancement by using anisotropic filter and CLAHE

The purpose of image enhancement is to process an acquired image for better contrast and visibility of features of interest for visual examination as well as subsequent computer-aided analysis and diagnosis. Therefore, we have proposed an algorithm for medical images enhancement. In the study, we used top-hat transform, contrast limited histogram equalization and anisotropic diffusion filter methods. The system results are quite satisfactory for many different medical images like lung, breast, brain, knee and etc.

Automatic Detection of Anthropometric Features from Facial Images

In this study we try to detect anthropometric features and estimate age from facial images. We designed a neural network and trained it for face detection. In order to locate the facial features we calculate the vertical and horizontal projections and search them for minimums and maximums. Later we calculate some geometrical ratios and differences which are used for age estimation. Experimental results show that our algorithm can detect the face and facial features successfully.

A new secret image sharing technique based on Asmuth Bloom's scheme

The Chinese Remainder Theorem (CRT) is used for secret sharing by both Mignotte and Asmuth Bloom in 1983. Then Shyu et al. used Mignottes scheme in the field of secret image sharing in 2008. However, their method use a Pseudo Random Number Generator (PRNG) with a seed to generate different pixel values for the consecutive secret pixels that have the same value. The need to distribute the seed and PRNG function to participants in order to reconstruct the secret image is a drawback of their method. A modified secret image sharing technique based on Asmuth Blooms secret sharing scheme is proposed in this paper. It does not require to distribute the seed or PRNG like Shyu et al.s technique. In addition, PRNG function is not used during decoding. Therefore, drawbacks in Shyu et al.s scheme is eliminated by the proposed method using Asmuth Blooms scheme as can be seen in the results.

Age Estimation Based on Local Radon Features of Facial Images

This paper proposes a new age estimation method relying on regional Radon features of facial images and regression. Radon transform converts a pixel represented image an equivalent, lower dimensional and more geometrically informative Radon pixel image and it brings a large advantage achieving global geometric affine invariance. Proposed method consists of four modules: preprocessing, feature extraction with Radon transform, dimensionality reduction with PCA and age estimation with multiple linear regression. We conduct our experiments on FG-NET, MORPH and FERET databases and the results have shown that proposed method has better results than many conventional methods on all databases.

Secret image sharing with reversible capabilities

Secret image sharing is a technique to share a secret image among n participants using Shamirs secret sharing scheme. Secret image is revealed if any k of the n shares is processed according to the scheme. Research reported in the literature is focused on improving known issues of the method. Reconstruction without distortion, reducing the size expansion of the share images, improving stego image quality and enhancing authentication ability of the method are some of the issues. Recovering cover images after the revealing procedure is an important issue. In 2009, Wu et al. proposed a technique based on reversible steganography to solve this problem. A location map is used to recover cover images, which needs extra information. The proposed method outlined in this paper does not need any information except shares to recover cover images. In addition, visual quality of the shares or the peak signal to noise ratio (PSNR) values of stego images are improved which is used to demonstrate the effectiveness of the method. Experimental results indicate a 3 dB PSNR improvement on the average compared to Wu et al.s method.

Secret image sharing with enhanced visual quality and authentication mechanism

Abstract Secret image sharing is a technique to share a secret image among n participants. Each participant has a meaningless, noise-like share. The image is revealed if any k of the shares are gathered. This scheme uses the polynomial based (k, n) secret sharing approach proposed by Shamir in 1979. In 2004, Lin and Tsai proposed a new secret image sharing method with steganography. Their scheme uses steganography to hide the shares into cover images. After this pioneering research, Yang et al. proposed a technique with enhanced stego image quality and better authentication ability in 2007. Wu et al. proposed another method to both decrease size expansion ratio of stego images and increase stego image quality by 0·5 dB compared to Yang et al.’s method in 2009. A new method with better authentication ability and stego image quality is proposed in this manuscript. More natural looking stego images of 43 dB peak signal-to-noise-ratio (PSNR) are generated by the proposed method exceeding Wu et al.’s method by 1·2 dB on the average. Also proposed method can detect fake stego blocks with probability 0·875 while other methods could detect with probability 0·5. The experimental results indicate enhanced authentication ability and visual quality compared to other methods.