As part of the early warning system, forest fire detection has a critical role in detecting fire in a forest area to prevent damage to forest ecosystems. In this case, the speed of the detection process is the most critical factor to support a fast response by the authorities. Thus, this article proposes a new framework for fire detection based on combining color-motion-shape features with machine learning technology. The characteristics of the fire are not only red but also from their irregular shape and movement that tends to be constant at specific locations. These characteristics are represented by color probabilities in the segmentation stage, color histograms in the classification stage, and image moments in the verification stage. A frame-based evaluation and an intersection over union (IoU) ratio was applied to evaluate the proposed framework. Frame-based evaluation measures the performance in detecting fires. In contrast, the IoU ratio measures the performance in localizing the fires. The experiment found that the proposed framework produced 89.97% and 10.03% in the true-positive rate and the false-negative rate, respectively, using the VisiFire dataset. Meanwhile, the proposed method can obtain an average of 21.70 FPS in processing time. These results proved that the proposed method is fast in the detection process and can maintain performance accuracy. Thus, the proposed method is suitable and reliable for integrating into the early warning system.

Abnormal erythrocytes have diverse shapes. The appearance of specific erythrocyte shapes in a person’s blood can indicate certain diseases, including thalassemia. We used thalassemia peripheral blood smear images and applied a segmentation process to produce single erythrocyte sub-images. Each erythrocyte has a unique shape. The selection of appropriate features to represent erythrocytes is critical for classification accuracy. We used morphological features such as moment invariants, geometry parameters of the cell and central pallor, and distance angle signature (DAS) morphological features of the cell and central pallor. We combined morphological features with texture and color features to increase the accuracy of erythrocyte classification. In this study, the multi-layer perceptron is used to classify nine shapes of erythrocytes present in thalassemia cases. The experimental results of 7108 erythrocytes indicated an accuracy of 98.11% based on the combination of features. The experimental results also show that the combination of features we proposed produced higher classification accuracy than previous work, which yielded an accuracy of 93.77%.

Hematological disorders of leukocytes (white blood corpuscles) are very frequent in medical practices. Each year, the number of new cases of leukemia increased with a high mortality rate what can cause a delay in diagnosis and treatment of leukemia. The hematologist faces difficulty in classifying white blood cells included cancerous leukemia cells. Currently, the diagnosis of hematological disorder was made by microscopic analysis of peripheral blood smear by hematological experts. However, this kind of diagnosis is complex, costly process, time-consuming and inherently subjective, hence to avoid such problems a classification technique based on computer vision is required. This document provides a survey of many kinds of literature which talk about leukemia detection using image processing. In this year, many improvements were made in this field. With this document, we provide a new perspective from many kinds of literature so future research can be developed effectively for their research.

Batik is a text ile with mot ifs of Indonesian culture wh ich has been recognized by UNESCO as world cultural heritage. Bat ik has many motifs which are classified in various classes of batik. This study aims to combine the features of texture and the feature of shapes' ornament in batik to classify images using artificial neural networks. The value of texture features of images in batik is extracted using a gray level co-occurrence matrices (GLCM) wh ich include Angular Second Moment (ASM) / energy), contrast, correlation, and inverse different mo ment (IDM). The value of shape features is extracted using a binary mo rphological operation which includes compactness, eccentricity, rectangularity and solidity. At this phase of the training and testing, we compare the value of a classification accuracy of neural networks in each class in batik with their texture features, their shape, and the combination of texture and shape features. From the three features used in the classification of batik image with artificial neural networks, it was obtained that shape feature has the lowest accuracy rate of 80.95% and the combination of texture and shape features produces a greater value of accuracy by 90.48%. The results obtained in this study indicate that there is an increase in accuracy of batik image classification using the artificial neural network with the co mb ination of texture and shape features in batik image.

Septiarini A, et al. Healthc Inform Res. 2018 Oct;24(4):335-345. https://doi.org/10.4258/hir.2018.24.4.335