In recent years, massive outbreaks of the European spruce bark beetle ( Ips typographus , (L.)) have caused colossal harm to coniferous forests. The main solution for this problem is the timely prevention of the bark beetle spread, for which it is necessary to identify damaged trees in their early stages of infestation. Fortunately, high-resolution unmanned aerial vehicle (UAV) imagery together with modern detection models provide a high potential for addressing such issues. In this work, we evaluate and compare three You Only Look Once (YOLO) deep neural network architectures, namely YOLOv2, YOLOv3, and YOLOv4, in the task of detecting infested trees in UAV images. We built a new dataset for training and testing these models and used a pre-processing balance contrast enhancement technique (BCET) that improves the generalization capacity of the models. Our experiments show that YOLOv4 achieves particularly good results when applying the BCET pre-processing. The best test result when comparing YOLO models was obtained for YOLOv4 with the mean average precision up to 95%. As a result of applying artificial data augmentation, the improvement for models YOLOv2, YOLOv3, and YOLOv4 was 65.0%, 7.22%, and 3.19%, respectively.

Monitoring the structure parameters and damage to trees plays an important role in forest management. Remote-sensing data collected by an unmanned aerial vehicle (UAV) provides valuable resources to improve the efficiency of decision making. In this work, we propose an approach to enhance algorithms for species classification and assessment of the vital status of forest stands by using automated individual tree crowns delineation (ITCD). The approach can be potentially used for inventory and identifying the health status of trees in regional-scale forest areas. The proposed ITCD algorithm goes through three stages: preprocessing (contrast enhancement), crown segmentation based on wavelet transformation and morphological operations, and boundaries detection. The performance of the ITCD algorithm was demonstrated for different test plots containing homogeneous and complex structured forest stands. For typical scenes, the crown contouring accuracy is about 95%. The pixel-by-pixel classification is based on the ensemble supervised classification method error correcting output codes with the Gaussian kernel support vector machine chosen as a binary learner. We demonstrated that pixel-by-pixel species classification of multi-spectral images can be performed with a total error of about 1%, which is significantly less than by processing RGB images. The advantage of the proposed approach lies in the combined processing of multispectral and RGB photo images.

Image processing techniques play an important role in the diagnostics and detection of diseases and monitoring the patients having these diseases. Breast Cancer detection of medical images is one of the most important elements of this field. Because of low contrast and ambiguous the structure of the tumor cells in breast images, it is still a challenging task to automatically segment the breast tumors. Our method presents an innovative approach to the diagnosis of breast tumor incorporates with some noise removal functions, followed by improvement features and gain better characteristics of medical images for a right diagnosis using balance contrast enhancement techniques (BCET). The results of second stage is subjected to image segmentation using Fuzzy c-Means (FCM) clustering method and Thresholding method to segment the out boundaries of the breast and to locate the Breast Tumor boundaries (shape, area, spatial sizes, etc.) in the images. The third stage feature extraction using Discrete Wavelet Transform (DWT). Finally the artificial neural network will be used to classify the stage of Breast Tumor that is benign, malignant or normal. The early detection of Breast tumor will improves the chances of survival for the patient. Probabilistic Neural Network (PNN) with radial basis function will be employed to implement an automated breast tumor classification. The simulated results shown that classifier and segmentation algorithm provides better accuracy than previous method. Proper segmentation is mandatory for efficient feature extraction and classification.

Medical image processing is the most challenging and emerging field nowadays. Edge detection of MRI images is one of the most important elements of this field. This paper describes the proposed strategy to detect the edges of brain tumor from patient's MRI scan images of the brain. This method incorporates with some noise removal functions, followed by improvement features and gain better characteristics of medical images for a right diagnosis using BCET. The result of second stage is subjected to image segmentation by using Fuzzy c-Means (FCM) clustering method. Finally, canny edge detection method is applied to detect the fine edges. For the experimental study we used images containing brain tumors that were characterized by different location, type of pathology, shape, size and density, as well as the size of the area of the affected tissue near the tumor space. Detection and extraction of tumor from MRI scan images of the brain is done by using MATLAB software. The result of studies of the experimental material with usage of the proposed methodology demonstrates some resistivity to a noise. Also, an increase in the accuracy of solving the problems of geometric analysis and segmentation, in some cases of tumor pathology, was found to be up to 10-15% better relative to the corresponding expert estimates.