Automated Segmentation of Nucleus And Cytoplasm of Cervical Cells From Pap-Smear Images Using A Quadtree Decomposition Approach.

Background: Digital pathology and microscopy image analysis is widely used for comprehensive studies of cell morphology especially for cervical cancer screening from pap-smears. Manual assessment of pap-smears is labour intensive and prone to interobserver variations. Computer-aided methods, which can significantly improve the objectivity and reproducibility, have attracted a great deal of interest in recent literature. A critical prerequisite in automated analysis of pap-smears is nucleus and cytoplasm segmentation, which is the basis of cervical cancer screening. This paper articulates a potent approach to the segmentation of cervical cells into nucleus and cytoplasm using a quadtree decomposition approach with statistical measures.Results: Choosing an appropriate quadtree decomposition strategy was a great challenge and a novel task in the proposed approach. The image is pre-processed using an enhanced median filter and is decomposed based on the mean, maximum entropy and the variance statistical measures of the pixels in the subtree. As a result, highly efficient and segmentations of acceptable performance were obtained. Comparison of the segmented nucleus and cytoplasm with the ground truth nucleus and cytoplasm segmentations resulted into a Zijdenbos similarity index of greater than 0.9034 and 0.9498 for nucleus and cytoplasm segmentation respectively. Conclusion: Given the accuracy of the classifier in segmenting the nucleus which plays an important role in cervical cancer diagnosis and classification, the classifier can be adapted for automated systems for cervical cancer diagnosis and classification. The method serves as a basis for first level segmentation of cervical cells for diagnosis and classification of cervical cancer from pap-smears.

Design and Development of a Hardware Efficient Image Compression Improvement Framework

Background: In the region of image processing, a varied number of methods have already initiated the concept of data sciences optimization, in which, numerous global researchers have put their efforts upon the reduction of compression ratio and increment of PSNR. Additionally, the efforts have also separated into hardware and processing sections, that would help in emerging more prospective outcomes from the research. In this particular paper, a mystical concept for the image segmentation has been developed that helps in splitting the image into two different halves’, which is further termed as the atomic image. In-depth, the separations were done on the bases of even and odd pixels present within the size of the original image in the spatial domain. Furthermore, by splitting the original image into an atomic image will reflect an efficient result in experimental data. Additionally, the time for compression and decompression of the original image with both Quadtree and Huffman is also processed to receive the higher results observed in the result section. The superiority of the proposed schemes is further described upon the comparison basis of performances through the conventional Quadtree decomposition process. Objective : The objective of this present work is to find out the minimum resources required to reconstruct the image after compression. Method : The popular method of quadtree decomposition with Huffman encoding used for image compression. Results : The proposed algorithm was implemented on six types of images and got maximum PSNR of 30.12dB for Lena Image and a maximum compression ratio of 25.96 for MRI image. Conclusion: Different types of images are tested and a high compression ratio with acceptable PSNR was obtained.