Harumanis Mango Leaves Image Segmentation on RGB and HSV Colour Spaces using Fast k-Means Clustering

Harumanis mango is the signature fruit in Perlis due to its delicious taste and its sweet-smelling. A good quality Harumanis tree requires rich in nutrition (healthy), and the tree will grow lots of fruits compared to the trees which are poor in nutrition (unhealthy). The health condition of a tree can be observed through the leaves in term of shape of leaves. For a healthy Harumanis tree, the leaves grow in scattering shapes. Meanwhile, an unhealthy Harumanis tree grows in gathered shapes. Therefore, this research is focusing on Harumanis mango leaves image segmentation by comparing between RGB and HSV colour spaces in order to obtain the best segmentation performance. 100 of Harumanis mango tree leaves images are used in this research. These images have undergo through image pre-processing such as modified linear contrast stretching and colour components extraction based on RGB and HSV colour spaces. Then, the colour component images have been segmented by using fast k-means clustering in order to obtain the leaves segmented images. Finally, quantitative analyses have been performed to measure the segmentation performance based on sensitivity, specificity and accuracy. Overall, the results show that S component of HSV colour space archives the highest accuracy with 85.81%.

Klasifikasi Tekstur Serat Kayu pada Citra Mikroskopik Veneer Memanfaatkan Deep Convolutional Neural Network

Convolutional Neural Network sebagai salah satu metode Deep Learning yang paling sering digunakan dalam klasifikasi, khususnya pada citra. Terkenal dengan kedalaman dan kemampuan dalam menentukan parameter sendiri, yang memungkinkan CNN mampu mengeksplor citra tanpa batas. Tujuan penelitian ini adalah untuk meneliti klasifikasi tekstur serat kayu pada citra mikroskopik veneer dengan CNN. Model CNN akan dibangun menggunakan MBConv dan arsitektur lapisan akan didesain menggunakan EfficientNet. Diharapkan dapat tercapai tingkat akurasi yang tinggi dengan penggunaan jumlah parameter yang sedikit. Dalam penelitian ini akan mendesain empat model arsitektur CNN, yaitu model RGB tanpa contrast stretching, RGB dengan contrast stretching, Grayscale tanpa contrast stretching dan Grayscale dengan contrast stretching. Proses ujicoba akan mencakup proses pelatihan, validasi dan uji pada masing-masing input citra pada setiap model arsitektur. Dengan menggunakan penghitungan softmax sebagai penentu kelas klasifikasi. SGD optimizer digunakan sebagai optimization dengan learning rate 1e-1. Hasil penelitian akan dievaluasi dengan menghitung akurasi dan error dengan menggunakan metode F1-score. Penggunaan channel RGB tanpa contrast stretching sebagai citra input menunjukkan hasil uji coba yang terbaik.

Fast Segmentation Algorithm for Cystoid Macular Edema Based on Omnidirectional Wave Operator

Optical coherence tomography (OCT) is widely used in the field of ophthalmic imaging. The existing technology cannot automatically extract the contour of the OCT images of cystoid macular edema (CME) and can only evaluate the degree of lesions by detecting the thickness of the retina. To solve this problem, this paper proposes an automatic segmentation algorithm that can segment the CME in OCT images of the fundus quickly and accurately. This method firstly constructs the working environment by denoising and contrast stretching, secondly extracts the region of interest (ROI) containing CME according to the average gray distribution of the image, and then uses the omnidirectional wave operator to perform multidirectional automatic segmentation. Finally, the fused segmentation results are screened by gray threshold and position feature, and the contour extraction of CME is realized. The segmentation results of the proposed method on data set images are compared with those obtained by manual marking of experts. The accuracy, recall, Dice index, and F1-score are 88.8%, 75.0%, 81.1%, and 81.3%, respectively, with the average process time being 1.2 s. This algorithm is suitable for general CME image segmentation and has high robustness and segmentation accuracy.

Identification of Suitable Contrast Enhancement Technique for Improving the Quality of Astrocytoma Histopathological Images.

Contrast enhancement plays an important part in image processing. In histology, the application of a contrast enhancement technique is necessary since it can help pathologists in diagnosing the sample slides by increasing the visibility of the morphological and features of cells in an image. Various techniques have been proposed to enhance the contrast of microscopic images. Thus, this paper aimed to study the effectiveness of contrast enhancement techniques in enhancing the Ki67 images of astrocytoma. Three contrast enhancement techniques consist of contrast stretching, histogram equalization, and CLAHE techniques were proposed to enhance the sample images. The performance of each technique was compared by computing seven quantitative measures. The CLAHE technique was preferred for enhancing the contrast of the astrocytoma images. This technique produces good results especially in contrast enhancement, edge conservation and enhancement, brightness preservation, and minimum distortions to the enhanced images.

Validation of the FPGA-Based Image Processing Techniques using the efficient tool like Xilinx Device Generators

Foremost Image Enhancement's intent is to analyze an image in a direction that the output becomes more appropriate for a particular application, rather than the original picture. Image enhancement methods include a multitude of options for enhancing the image accuracy of photographs. The appropriate choice of such strategies is strongly determined by the imaging modality. FPGA has several main features that can be used as a tool for the processing of authentic time algorithms. It gives significantly higher efficiency over the programmable processor. This paper presents information regarding FPGA implementation of Image Processing Algorithms using Xilinx System Generator (XSG). Xilinx Application Generator is a Xilinx existing application process that makes FPGA hardware design relatively easy. For synthesis and simulation, the Xilinx device generator is initiated with MATLAB. To reintroduce a wide range of image processing algorithms, a model-based analysis approach will be used. Various classification algorithms for RGB to grayscale, image negativity, image retrieval, contrast stretching, threshold, boundaries extraction, as well as various image fusion methods are explored, and therefore how they are implemented using available Device Generator components

Perbaikan Citra Menggunakan Metode Contrast Stretching

Contrasting images that are not good because they are too bright or too dark cannot provide good information. Therefore, a method is needed to improve the image quality, so that the information in the image can be conveyed properly. Contrast stretching is one of the methods for improving image quality. With this method is expected to produce a new image that is better. The purpose of this research is to apply contrast stretching method to an application or software that can be used to improve image quality. Data used in this study in the form of grayscale image data and RGB imagery (true color), with the format . BMP or .JPG, while the application development uses the Matlab programming language.The results of the study, contrast stretching method can be used to repair image that affects bad or poor image quality such as too bright / dark image, less sharp image, blurry, and so on. Contrast stretching method can also be used to improve image enhancement by leveling the histogram that was collected in an area, so that the information contained in the image is more clearly visible compared to the original image.