H. Abdul Karim

Reduced resolution depth coding for stereoscopic 3D video

In this paper, Reduced Resolution Depth Compression (RRDC) is proposed for Scalable Video Coding (SVC) to improve the 3D video rate distortion performance. RRDC is applied by using Down-Sampling and Up-Sampling (DSUS) of the depth data of the stereoscopic 3D video. The depth data is down-sampled before SVC encoding and up-sampled after SVC decoding operation. The proposed DSUS method reduces the overall bit rates and consequently: 1) improves SVC rate distortion for 3D video, particularly at lower bit rates in error free channels; and 2) improves 3D SVC performance for 3D transmission in error prone channels. The objective quality evaluation of the stereoscopic 3D video yields higher PSNR values at low bit rates for SVCDSUS compared to the original SVC (SVC-Org), which makes it advantageous in terms of reduced storage and bandwidth requirements. Moreover, the subjective quality evaluation of the stereoscopic 3D video further confirmed that the perceived stereoscopic 3D video quality of the SVC-DSUS is very similar to the stereoscopic 3D video of the SVC-Org by up to 98.2%.

Image skin segmentation based on multi-agent learning Bayesian and neural network

Skin colour is considered to be a useful and discriminating spatial feature for many skin detection-related applications, but it is not sufficiently robust to address complex image environments because of light-changing conditions, skin-like colours and reflective glass or water. These factors can create major difficulties in face pixel-based skin detectors when the colour feature is used. Thus, this paper proposes a multi-agent learning method that combines the Bayesian method with a grouping histogram (GH) technique and the back-propagation neural network with a segment adjacent-nested (SAN) technique based on the YCbCr and RGB colour spaces, respectively, to improve skin detection performance. The findings from this study have shown that the proposed multi-agent learning for skin detector has produced significant true positive (TP) and true negative (TN) average rates (i.e. 98.44% and 99.86% respectively). In addition, it has achieved a significantly lower average rate for the false negative (FN) and false positive (FP) (i.e. only 1.56% and 0.14% respectively). The experimental results show that multi-agent learning in the skin detector is more efficient than other approaches.

On the multi-agent learning neural and Bayesian methods in skin detector and pornography classifier: An automated anti-pornography system

The main objective on this study proposed anti-pornography system works on four machine learning methods in two different stages namely skin detector stage and pornography classifier stage. A multi-agent learning is used twice. In the first stage, we propose a multi-agent learning method that combines the Bayesian method with a grouping histogram (GH) technique and the back-propagation neural network with a segment adjacent-nested (SAN) technique based on the YCbCr and RGB colour spaces respectively, to extract skin regions from the image accurately with taking into consideration the problems of the light-changing conditions, skin-like colour and reflection from glass and water. In the second stage, the features from the skin are extracted to classify the images into either pornographic or non-pornographic. Inaccurate classification occurs when different image sizes are used in the existing anti-pornography systems. Thus, this paper proposes a multi-agent learning that combines the Bayesian method with a grouping histogram technique again to extract the features from the skin detection based on YCbCr colour space and the back propagation neural network method using shape features extracted again from skin detection. The classification of the pornographic images becomes more robust to the variation in images sizes. The findings from this study have shown that the proposed multi-agent learning system for skin detection has produced a significant rate of true positives (TP) (i.e., 98.44%). In addition, it has achieved a significant low average rate for the false positives (FP) (i.e., only 0.14%) while the proposed multi-agent learning for pornography classifier has produced significant rates of TP (i.e., 96%). Moreover, it has achieved a significant low average rate of FP (i.e., only 2.67%). The experimental results show that multi-agent learning in the skin detector and pornography classifier are more efficient than other approaches.

A new digital watermarking evaluation and benchmarking methodology using an external group of evaluators and multi‐criteria analysis based on ‘large‐scale data’

Digital watermarking evaluation and benchmarking are challenging tasks because of multiple evaluation and conflicting criteria. A few approaches have been presented to implement digital watermarking evaluation and benchmarking frameworks. However, these approaches still possess a number of limitations, such as fixing several attributes on the account of other attributes. Well‐known benchmarking approaches are limited to robust watermarking. Therefore, this paper presents a new methodology for digital watermarking evaluation and benchmarking based on large‐scale data by using external evaluators and a group decision making context. Two experiments are performed. In the first experiment, a noise gate‐based digital watermarking approach is developed, and the scheme for the noise gate digital watermarking approach is enhanced. Sixty audio samples from different audio styles are tested with two algorithms. A total of 120 samples were evaluated according to three different metrics, namely, quality, payload, and complexity, to generate a set of digital watermarking samples. In the second experiment, the situation in which digital watermarking evaluators have different preferences is discussed. Weight measurement with a decision making solution is required to solve this issue. The analytic hierarchy process is used to measure evaluator preference. In the decision making solution, the technique for order of preference by similarity to the ideal solution with different contexts (e.g., individual and group) is utilized. Therefore, selecting the proper context with different aggregation operators to benchmark the results of experiment 1 (i.e., digital watermarking approaches) is recommended. The findings of this research are as follows: (1) group and individual decision making provide the same result in this case study. However, in the case of selection where the priority weights are generated from the evaluators, group decision making is the recommended solution to solve the trade‐off reflected in the benchmarking process for digital watermarking approaches. (2) Internal and external aggregations show that the enhanced watermarking approach demonstrates better performance than the original watermarking approach.

A FOUR-PHASES METHODOLOGY TO PROPOSE ANTI-PORNOGRAPHY SYSTEM BASED ON NEURAL AND BAYESIAN METHODS OF ARTIFICIAL INTELLIGENCE

Pornographic images are disturbing and malicious contents that are easily available through Internet technology. It has a negative and lasting effect on children who use the Internet; thus, pornography has become a serious threat not only to Internet users but also to society at large. Therefore, developing efficient and reliable tools to automatically filter pornographic contents is imperative. However, the effective interception of pornography remains a challenging issue. In this paper, a four-phase anti-pornography system based on the neural and Bayesian methods of artificial intelligence is proposed. Primitive information on pornography is examined and then used to determine if a given image falls under the pornography category. First, we present a detailed description of preliminary study phase followed by the modeling phase for the proposed skin detector. An anti-pornography system is created in the development phase, which also includes the proposed pornography classifier based on skin detection. Finally, the performance assessment method for the proposed anti-pornography system is discussed in the evaluation phase.

AN AUTOMATED ANTI-PORNOGRAPHY SYSTEM USING A SKIN DETECTOR BASED ON ARTIFICIAL INTELLIGENCE: A REVIEW

Unprecedented advances in Internet technologies with multimedia capabilities have enabled pornography and adult content to be widely and freely distributed as easy as a click of a mouse through various means such as YouTube, Facebook, and Tags. Protecting children from unnecessary exposure to adult content has, therefore, become a serious problem in the real world. In particular, the considerable perversion in pornography and the exposure of children and the society to such perversions leads to moral decay. Constructing an appropriate filter for pornographic images is a major concern in modern society; however, this area poses challenges. This study aims to shed light on a content-based technique that employs an anti-pornography machine and to encourage researchers to study this adult image filtering technique. In this study, we discuss models of skin detection and their advantages and disadvantages in real life. We also elaborate on the pornographic image classifier using a feature extraction process and its classification process, along with the possible difficulties it may present. This study also analyzes anti-pornography techniques based on skin detection and discusses their strengths and weaknesses.

Further Reduced Resolution Depth Coding for stereoscopic 3D video

In this paper, Further Reduced Resolution Depth Coding (FRRDC) method is proposed as an improvement for the Reduced Resolution Depth Coding (RRDC) method that was used for Scalable Video Coding (SVC). Similar to RRDC, FRRDC is applied by using Down-Sampling and Up-Sampling (DSUS) of the depth data of the stereoscopic 3D video. The depth data is down-sampled before the SVC encoding and up-sampled after the SVC decoding operation. The proposed FRRDC using DSUS method aims to improve the coding method and efficiency of the RRDC method in terms of objective and subjective quality of the stereoscopic 3D video. The difference between FRRDC and RRDC method lies in the sense that FRRDC encodes an even more reduced resolution of the depth video compared to the RRDC. This paper gives an overview of the FRRDC method and the simulation results are obtained to evaluate the performance of the FRRDC method.

An error resilience method for depth in stereoscopic 3D video

Error resilience stereoscopic 3D video can ensure robust 3D video communication especially in high error rate wireless channel. In this paper, an error resilience method is proposed for the depth data of the stereoscopic 3D video using data partitioning. Although data partitioning method is available for 2D video, its extension to depth information has not been investigated in the context of stereoscopic 3D video. Simulation results show that the depth data is less sensitive to error and should be partitioned towards the end of the data partitions block. The partitioned depth data is then applied to an error resilience method namely multiple description coding (MDC) to code the 2D video and the depth information. Simulation results show improved performance using the proposed depth partitioning on MDC compared to the original MDC in an error prone environment.

Multiple description coding with side information for stereoscopic 3D

Stereoscopic video as the simplest form of 3D video is already being used in consumer devices such as 3DTV and 3D mobile phone. When the 3D video from the 3D mobile phone is compressed and transmitted over error prone channels, error propagation due to packet loss leads to poor 3D visual quality. The objective of the paper is to provide error resilience 3D video using the well known multiple description coding (MDC) technique. Specifically, the MDC is modified for 2D plus depth stereoscopic video with the addition of spatially reduced resolution of the side information. The proposed method reduces the depth bit rates and consequently: 1) improves their rate distortion, particularly at higher bit rates in error free channels; and 2) improves their performance in ideal MDC channel.

User perception evaluations of 3D video telephony as compared to actual experience for face-to-face immersive communications

User perception evaluations of an experimental 3D video communication system are conducted utilizing bilateral experimental setup. Subjective assessment method together with the 5-grade ITU-R quality and impairment scales are adopted in these evaluations. Two sets of experimental system are installed in two evaluation booths to emulate video communication between two users at two different locations. Evaluation items are categorized into two namely 3D effects related and system related. The results indicate that video communication through the system shows positive closeness to natural face-to-face communication and the eye contact level during video communication is the only significant limitation of the experimental system thus requires improvement.