Khalid M. Amin

Fully automatic liver tumor segmentation from abdominal CT scans

Liver cancer causes the majority of primary malignant liver tumors among adults. Computed Tomography (CT) scans are generally used to make the treatment plan or to prepare for ablation surgery. Processing CT image includes the automatic diagnosis of liver pathologies, such as detecting lesions and following vessels ramification, and 3D volume rendering. This paper presents a new fully automatic method to segment the tumors in liver structure with no interaction from user. Contrast enhancement is applied to the slices of segmented liver, then adding each image to itself to have a white image with some pepper noise and tumors as dark gray spots. After applying Gaussian smoothing, Isodata threshold is used to turn the image into binary with tumors as black spots on white background. Tests are reported on abdominal datasets showing promising result.

A novel fully automatic technique for liver tumor segmentation from CT scans with knowledge-based constraints

The liver is a common site for the occurrence of tumors. Automatic hepatic lesion segmentation is a crucial step for diagnosis and surgery planning. This paper presents a new fully automatic technique to segment the tumors in liver structure with no interaction from user. Contrast enhancement is applied to the slices of segmented liver, then adding each image to itself to have a white image with some pepper noise and tumors as dark gray spots. After applying Gaussian smoothing, Isodata is used to threshold the tumor in the slice. In order to eliminate erroneous segmentation a discriminative rule based on diagnostic knowledge on liver cancer shape is applied. Finally, a 3-D consistency check is performed based on three-dimensional information that a lesion mass cannot appear in a single slice independently. Tests are performed on abdominal datasets showing promising result. Using MICCAI 2008 segmentation evaluation metrics, the novel proposed technique achieved 80.19 as a total score.

Automatic liver tumor segmentation from CT scans with knowledge-based constraints

Automatic hepatic tumor segmentation is a crucial step for diagnosis and surgery planning. This paper presents a new fully automatic technique to segment the tumors in liver structure with no interaction from user. Contrast enhancement is applied to the slices of segmented liver, then adding each image to itself to have a white image with some pepper noise and tumors as dark gray spots. After applying Gaussian smoothing, Isodata is used to threshold the tumor in the slice. In order to eliminate erroneous segmentation, discriminative rule based on diagnostic knowledge on liver cancer shape is applied along with a 3-D consistency check is performed based on three-dimensional information that a lesion mass cannot appear in a single slice independently. Tests are performed on 9 abdominal datasets and promising result shows that sensitivity and specificity for automatic liver tumor segmentation are 87% and 99% respectively.

An Automated approach for Preventing ARP Spoofing Attack using Static ARP Entries

ARP spoofing is the most dangerous attack that threats LANs, this attack comes from the way the ARP protocol works, since it is a stateless protocol. The ARP spoofing attack may be used to launch either denial of service (DoS) attacks or Man in the middle (MITM) attacks. Using static ARP entries is considered the most effective way to prevent ARP spoofing. Yet, ARP spoofing mitigation methods depending on static ARP have major drawbacks. In this paper, we propose a scalable technique to prevent ARP spoofing attacks, which automatically configures static ARP entries. Every host in the local network will have a protected non-spoofed ARP cache. The technique operates in both static and DHCP based addressing schemes, and Scalability of the technique allows protecting of a large number of users without any overhead on the administrator. Performance study of the technique has been conducted using a real network. The measurement results have shown that the client needs no more than one millisecond to register itself for a protected ARP cache. The results also shown that the server can a block any attacker in just few microsecond under heavy traffic.

Artificial bee colony optimizer for historical Arabic manuscript images binarization

Historical manuscript image binarization is a very important step towards full word spotting system. In this paper, we present a novel binarization algorithm based on artificial bee colony optimizer. The proposed approach contains two phases. The first phase is stretching the intensity level of the image by contrast stretching filter and removing the noise by image cleaning algorithm, the second phase is determining the number of clusters, number of colony and iterations for starting Artificial Bee Colony (ABC) algorithm. The proposed approach is tested on a set of images collected from the electronic Arabic manuscripts database and compared against three famous binarization methods such as Niblacks, Otsus and Savouls. The Experimental results show that the proposed approach is a promising approach and can obtain the desired results better than the other compared methods.

Improved text-independent speaker identification system for real time applications

Speaker identification identifies the speaker among a set of users by matching against a set of voiceprints. In speaker identification, the identification time depends on the number of feature vectors, their dimensionality and the number of speakers. In this paper, text independent speaker identification model is developed by taking in MFCCs with VQ to obtain pressed feature vectors without losing much information, and the numbers of speakers are reduced in the test by gender detection algorithm. Gaussian Mixture Model (GMM) is used a modeling technique. Results show that proposed approach always yields better improvements in accuracy and brings almost 50% reduces in time processing.

Detection and correction of deformed historical arabic manuscripts

Historical manuscripts are considered one of the most imperative human riches and a source of intellectual production. Unfortunately, due to aging effects, multiple noises and deviations are found in the document image. Moreover, challenges for several images of ancient documents show defects of inclinations and curvatures of text lines. These defects arise due to bad storage conditions, or during the digitization process. In order to improve the readability and the automatic recognition of historical Arabic manuscripts, preprocessing steps are imperative. This paper presents a novel method that consists of two major phases. The first refer to binarization and enhancement of the scanned document image. In the second phase, correction of skew angle in the text line passes by the detection of curvature/inclination of the baseline. Then, calculating the skewed angle of this line, and finally, correcting the line with a rotation relative to its centre. The proposed method was implemented on different scanned Arabic documents. The proposed methodology overcomes the defects of global binarization method, also, save the high computation effort of adaptive binarization techniques. Moreover, it works well with both Arabic handwritten words and printed text.