Mohd Nizam Saad

Image segmentation for lung region in chest X-ray images using edge detection and morphology

Studies of medical image segmentation have long been done as a mean to distinguish object region from one to another for further image analysis. The segmentation of lung region in chest X-ray (CXR) based on object edge detection is one of the popular method applied. Early edge detection algorithms like Sobel, Prewitt and Laplacian have been used to segment the lung however, none of them can successfully generate a truly satisfied segmentation output. The reason for this fail is because they are high pass filter that is sensitive to image noise. Hence, the requirement for better edge detection algorithm that can cope with reasonable lower and upper threshold value for image noise like canny edge should be highlighted. Moreover, combining this algorithm with morphology method (dilation and erosion) will produce better outcome. Therefore, this paper has proposed method for segmenting lung region in CXR images using canny edge filter and morphology. Although the filter can detect the lung edge, unfortunately, the final edges lines produce are still unsatisfied. To solve the problem, Euler number method is applied to extract the lung region before executing the edge detection using the filter. The implementation produced convincing result as most of the segmented image is almost similar to the ground truth image.

Redesigning the user interface of handwriting recognition system for preschool children

Nowadays there are handwriting recognition systems that can be occupied to assist children learning how to write properly. However, one of the major barriers that hinders them using the system is its complex user interface where the designed is based on adult preferences. Therefore in this paper, we present the guideline to redesign the user interfaces via our experience developing a handwriting recognition system for pre-school children named Handwriting-based Learning Number (HLN). The redesign process has followed eight guidelines and rules as presented by Schniederman. The user interface satisfaction evaluation result done using Questionnaire for User Interface Satisfaction (QUIS) is very convincing where the users are almost satisfied with the redesign process that we did to the user interface. Hence we found that the guidelines are very useful and developers are all welcome to follow it if they intend to do similar system like us.

The spatial relation features for describing objects relationships within image

Spatial features has gained attention in CBIR researches as a mean to represent image properties. These features, presented via Spatial Relation Features (SRF) such left, right, on and in can provide fine queries to locate object location as well as its relation with other object within an image. Although spatial features play an important, yet, there is still less effort done to collect them in proper manner which yield difficulties to use them for spatial-based image processing research. In order to overcome this lack, we presented our library research work in finding the SRF that have been used in computer science research for describing objects spatial relationships within image. Our work managed to produce collection of SRF found in prior literatures which are later listed and described in proper tables. Apart from that, we also described categories that are used to group these SRF in fine arrangement based on their usage. After updated the SRF list, we manage to derive 24 set of SRF recorded under three categories namely topology, orientation and metric.

The adaptation of handwriting recognition system user interface in preschool literacy learning courseware

Currently, the education software or simply courseware has successfully become the heart of computer usage in classrooms. With varieties of courseware introduced, the discussion of which courseware assist students the most continues. This paper describes our experience on developing a literacy courseware named handwriting leaning number (HLN) for preschool children.HLN has adapted the handwriting recognition system interface where stylus pen becomes its input modality.By using the stylus pen, we believed that the children could perform better in writing exercise.In order to prove our assumption, we have conducted user satisfaction test using modified questionnaire for user interface satisfaction (QUIS) version 5.5.Result derived from the test indicated that the children tend to satisfy the user interface designed for HLN as the average mean score obtained was 3.864 with Standard Deviation of 0.6879.On the other hand, problems regarding precision and usability of HLN are also reported while solutions to the problems are recommended.