No abstract

The karyotyping technique is importance in the diagnosis of genetic diseases of humans, including the diagnosis the genetic disorders of prenatal and cancer. In order to obtain the karyotype system for the metaphase images of chromosomes using the image processing. Assembling of human chromosomes pairs from the metaphase image will pass in several stages which are segmentation (single chromosome, overlapped and touching chromosome), feature extraction, matching and classification. In this study has been focus on the separation of touching and overlapped. The problem of separation touching and overlapped chromosome was solved using the convulsion mask and with a help the morphological thinning and contour. The separation of touching and overlapped chromosome is according on finding cut points. The thinning of the image is obtained which helps to identification the Region of Interest. The contour of the image is obtained which helps to explain the entire shape of the image and find out the cut points for separation between chromosomes. In this study an efficient algorithms was used to separation the cluster of touching and overlapping chromosomes. The algorithm of separation touching and overlapping was implemented by using sequential stages (initially, segmentation from metaphase image, convert to the binary image, extract thinning, using mask with 9*9, extract contour, using mask 7*7, identified the cut points and finally, separate touching or overlapping chromosome). This algorithm capable to isolate a cluster of touching chromosomes and a cluster of touching and overlapping chromosomes.

Extracting the remarkable attributes of the image objects is an issue of ongoing research special in the face recognition problem. This paper presents two directions. The first is a comparison between the local binary patterns (LBP) and its modified center symmetric LBP drawn from localized facial expressions and due to the efficiency, K-nearest neighbor (KNN) and the support vector machine (SVM) techniques play significant roles in this research used to implement the proposed system efficiently. The second direction proposes an efficient architecture by depending on deep learning convolution neural network (CNN) to implement face recognition. Such a design consists of two parts: a convolutional learning feature model and a classification model. The first one learns the important feature,while the second part produces a score class for each sample input. Many experiments are implemented on the known dataset once for the number of nearest neighbors (K value), and then decrease the number of expression samples for each individual the other time. The cross-validation method is used to provide a true picture of the accuracy of the face recognition system. In all experiment results, the center symmetric LBP with KNN outperforms the classic LBP. While significant progress in the results accuracy recognition ratio of the CNN model compared with other methods used.

No abstract

No abstract