Image segmentation is a wide research topic; a huge amount of research has been performed in this context. Image segmentation is a crucial procedure for most object detection, image recognition, feature extraction, and classification tasks depend on the quality of the segmentation process. Image segmentation is the dividing of a specific image into a numeral of homogeneous segments; therefore, the representation of an image into simple and easy forms increases the effectiveness of pattern recognition. The effectiveness of approaches varies according to the conditions of objects arrangement, lighting, shadow, and other factors. However, there is no generic approach for successfully segmenting all images, where some approaches have been proven to be more effective than others. The major goal of this study is to provide summarize of the disadvantages and the advantages of each of the reviewed approaches of image segmentation.

Data clustering is an important machine-learning topic. It is useful for variety of applications one of them is image segmentation. A given divided image into regions homogenous additional to certain features is the image segmentation process, which matches real objects of an actual scene. FIS (Food Image Segmentation) is important for calories estimation. K-means has been used for performing such task. However, in order to conclude the food items number in the image, it requires interacting with the application. This article, presents a novel approach based dependently on k-means named Hk-means (Homogeneity test of k-means) is developed to calculate k value and applied for FIS for the purpose of assuring full autonomy in the calories estimation system. This approach uses the homogeneity test so as to compensate the new item existence in the image. The suggested method Hk-means is tested on food images and show accuracy 96%. The experimental results has achieved 1.5 second execution time when compare with benchmark method.

Microscopic examination can be used to make a preliminary diagnosis of fungal infections. Due to their apparent similarities, it frequently does not allow for the species to be identified clearly. Therefore, additional biochemical tests are typically required. This adds extra expenses and can make the identification process last up to ten days. Given the high death rate for immunosuppressed patients, such a delay in the adoption of targeted therapy could have serious consequences. The fast learning network method is an alternative that provides information with a unique approach to predicting black fungus. The experimental results of prediction showed that the performance of the fast learning method is superior as compared with the five algorithms used in this paper.

The diagnosis of Parkinson has become easier with the existence of machine learning. It includes using existing features from the biometric dataset generated by the person to identify whether he has Parkinson or not. The features differ in their discrimination capability and they suffer from redundancy. Hence, researchers have recommended using feature selection for Parkinson's identification. The feature selection aims at finding the most important and relevant features to produce an efficient and effective model. In this article, we present entropy-based Parkinson classification. The goal is to select only 50% of the most relevant features for Parkinson prediction. Two variants of neural networks are used for evaluation, the first one is a feed-forward Extreme Learning Machine ELM and the second one is Fast Learning Machine FLN. Also, the K-Nearest Neighbor KNN algorithm is used for evaluation. The results show the superiority of ELM and FLN when the model of feature selection is used with an accuracy of 80% compared with only 78% when the model is not used.