163 research outputs found
Factors Affecting the Effectiveness of Anti- Money Laundering Practices in UAB Bank (Kay Thi Win Hlaing, 2025)
No full textThis study explores the factors affecting the effectiveness of Anti-Money
Laundering (AML) compliance practices at uab bank, a major private financial institution
in Myanmar. The research focuses on four key variables: the responsibility of the bank in
AML efforts, employee training and awareness, technological integration, and regulatory
enforcement. Data were collected from 385 respondents across various departments and
positions within uab bank through a structured questionnaire. The analysis involved
descriptive statistics, Pearson correlation, and multiple regression techniques. Findings
indicate that regulatory enforcement has the strongest positive effect on AML compliance,
followed by employee training and the bank’s internal responsibility. Technological
integration, while supportive, showed a relatively weaker influence. Overall, the results
suggest that AML compliance at uab Bank is at a high level, but continued improvement is
necessary, especially in system upgrades and proactive regulatory alignment. The study
concludes with recommendations aimed at strengthening compliance frameworks and
fostering a culture of integrity and accountability
Efficient Interactive Segmentation using Modified Maximal Similarity Region Merging
No full textInteractive image segmentation has manyapplications in image processing, computervision, computer graphics and medical imageanalysis. In medical applications, imagesegmentation is a fundamental process in mostsystems that support medical diagnosis, surgicalplanning and treatments. In many editing tasks,the aim is to separate a foreground object fromits background. Therefore, we propose a fast andsimple interactive image segmentation techniquein this paper. The proposed methodautomatically merges the regions that areinitially segmented by mean shift segmentation,and then effectively extracts the object contourby labeling all the non-marker regions as eitherbackground or object. Moreover, manyexperiments are tested and the results show thatthe proposed method is faster than the existingmethod. Therefore, the proposed method iseffective and can quickly and accurately segmentfor both medical and natural scene images with ease
Natural Scene Interactive Segmentation Using Edge Detection and Maximal Similarity Region Merging
No full textA fundamental problem in image processing isimage segmentation. The conventional imagesegmentation methods, to some extent, all suffer fromthe problem of inaccurate segmentation. A slightlyeasier and more approachable problem, interactivesegmentation, has also received a lot of attentions overthe years. In this paper, we propose a fast and simpleinteractive image segmentation technique. Thissegmentation process is conducted in two modules.First, the original image is detected by canny edgedetection method. Second, the object ofinterest issegmented by using the region merging based onmaximal similarity. In this work, color feature is usedto measure the closeness between two regions andaccordingly the label of the unmarked region isdecided. The proposed method extracts the object fromthe complex background in the image. Theeffectiveness of the proposed method is validated byexperimental results and compared with other method
Disparity Map Computation from Stereo Images Using Hill-Climbing Segmentation
No full textStereo matching is one of the most active research areas in computer vision for decades. The task of stereo matching is to find the point correspondence between two images of the same scene taken from different viewpoints. This paper presents a segment-based stereo matching algorithm. Firstly, the reference image is segmented using hill-climbing algorithm and local stereo matching is performed Scale Invariant Feature Transform (SIFT) feature points with Sum of Absolute Differences (SAD) block matching. Secondly, a set of reliable pixels is constructed by comparing the matching cost and the mutual cross-checking consistent between the left and right initial disparity maps, which can lead to an actual disparity plane. Thirdly, a set of all possible disparity planes are extracted and then plane fitting and neighboring segment merging are performed. Finally, the disparity planes are set in each region using graph cuts to obtain final disparity map. The evaluation of proposed algorithm on the Middlebury data set result shows that the proposed algorithm is competitive with state-of-the-art stereo matching algorithms
Entropy based Test Cases Reduction Algorithm for User Session based Testing
No full textEntropy based test cases reduction algorithm is implemented with the analytical results in terms of URL coverage, reduction time and test cases reduction rate
Test Cases Prioritization in User Session based Testing for Improving Fault Detection Rate
No full textWeb application testing has been usedin finding various faults in order to improve thequality of reliable web services. Among testcases generation approaches, user session basedtesting is an approach to create test cases withreal user data. However, real user data usage isextremely large and executing all the test casescan be time consuming in practice. Executing allthe tests in a reduced test suite can still be timeconsuming in practice. This paper describes thetest cases prioritization method to schedule thetest cases in order to improve the rate of faultdetection. This criterion is based on two factors,frequency (Feq) and dependent count (Dept) ofrequests. The average percent of fault detected(APFD) metric is used to reveal the permutationof test cases in a way may lead to fasterdetection available faults in a modified versionof web application
- …
