Offline handwritten signature is a type of behavioral biometric-based on an image. Its problem is the accuracy of the verification because once an individual signs, he/she seldom signs the same signature. This is referred to as intra-user variability. This research aims to improve the recognition accuracy of the offline signature. The proposed method is presented by using both signature length normalization and histogram orientation gradient (HOG) for the reason of accuracy improving. In terms of verification, a deep-learning technique using a convolution neural network (CNN) is exploited for building the reference model for a future prediction. Experiments are conducted by utilizing 4,000 genuine as well as 2,000 skilled forged signature samples collected from 200 individuals. This database is publicly distributed under the name of SIGMA for Malaysian individuals. The experimental results are reported as both error forms, namely False Accept Rate (FAR) and False Reject Rate (FRR), which achieved up to 4.15% and 1.65% respectively. The overall successful accuracy is up to 97.1%. A comparison is also made that the proposed methodology outperforms the state-of-the-art works that are using the same SIGMA database.
The disposal of textile effluents to the surface water bodies represents the critical issue especially these effluents can have negative impacts on such bodies due to the presence of dyes in their composition. Biological remediation methods like constructed wetlands are more cost-effective and environmental friendly technique in comparison with traditional methods. The ability of vertical subsurface flow constructed wetlands units for treating of simulated wastewater polluted with Congo red dye has been studied in this work. The units were packed with waterworks sludge bed that either be unplanted or planted with Phragmites australis and Typha domingensis. The efficacy of present units was evaluated by monitoring of DO, Temperature, COD
... Show MoreIn cognitive radio networks, there are two important probabilities; the first probability is important to primary users called probability of detection as it indicates their protection level from secondary users, and the second probability is important to the secondary users called probability of false alarm which is used for determining their using of unoccupied channel. Cooperation sensing can improve the probabilities of detection and false alarm. A new approach of determine optimal value for these probabilities, is supposed and considered to face multi secondary users through discovering an optimal threshold value for each unique detection curve then jointly find the optimal thresholds. To get the aggregated throughput over transmission
... Show MoreIndustrial effluents loaded with heavy metals are a cause of hazards to the humans and other forms of life. Conventional approaches, such as electroplating, ion exchange, and membrane processes, are used for removal of copper, cadmium, and lead and are often cost prohibitive with low efficiency at low metal ion concentration. Biosorption can be considered as an option which has been proven as more efficient and economical for removing the mentioned metal ions. Biosorbents used are fungi, yeasts, oil palm shells, coir pith carbon, peanut husks, and olive pulp. Recently, low cost and natural products have also been researched as biosorbent. This paper presents an attempt of the potential use of Iraqi date pits and Al-Khriet (i.e. substances l
... Show MoreIn this paper, method of steganography in Audio is introduced for hiding secret data in audio media file (WAV). Hiding in audio becomes a challenging discipline, since the Human Auditory System is extremely sensitive. The proposed method is to embed the secret text message in frequency domain of audio file. The proposed method contained two stages: the first embedding phase and the second extraction phase. In embedding phase the audio file transformed from time domain to frequency domain using 1-level linear wavelet decomposition technique and only high frequency is used for hiding secreted message. The text message encrypted using Data Encryption Standard (DES) algorithm. Finally; the Least Significant bit (LSB) algorithm used to hide secr
... Show MoreThe feature extraction step plays major role for proper object classification and recognition, this step depends mainly on correct object detection in the given scene, the object detection algorithms may result with some noises that affect the final object shape, a novel approach is introduced in this paper for filling the holes in that object for better object detection and for correct feature extraction, this method is based on the hole definition which is the black pixel surrounded by a connected boundary region, and hence trying to find a connected contour region that surrounds the background pixel using roadmap racing algorithm, the method shows a good results in 2D space objects.
Keywords: object filling, object detection, objec