Detection of Chicken Egg Embryos using BW Image Segmentation and Edge Detection Methods

This study aims to identify chicken egg embryos with the concept of image processing. This concept uses input and output in images. Thus the identification process, which was originally carried out using manual observation, was developed by computerization. Digital images are applied in identification by various image preprocessing, image segmentation, and edge detection methods. Based on these three methods, image processing has three processes: image grayscaling (convert to a grayscale image), image adjustment, and image enhancement. Image adjustment aims to clarify the image based on color correction. Meanwhile, image enhancement improves image quality, using histogram equalization (HE) and Contrast Limited Adaptive Histogram Equalization methods (CLAHE). Specifically for the image enhancement method, the CLAHE-HE combination is used for the improvement process. At the end of the process, the method used is edge detection. In this method, there is a comparison of various edge detection operators such as Roberts, Prewitt, Sobel, and canny. The results of edge detection using these four methods have the SSIM value respectively 0.9403; 0.9392; 0.9394; 0.9402. These results indicate that the SSIM values ​​of the four operators have the same or nearly the same value. Thus, the edge detection method can provide good edge detection results and be implemented because the SSIM value is close to 1.00 (more than 0.93). Image segmentation detected object (egg and embryo), and the continued process by edge detection showed clearly edge of egg and embryo.

New Stereo Vision Algorithm Composition Using Weighted Adaptive Histogram Equalization and Gamma Correction

This work presents the composition of a new algorithm for a stereo vision system to acquire accurate depth measurement from stereo correspondence. Stereo correspondence produced by matching is commonly affected by image noise such as illumination variation, blurry boundaries, and radiometric differences. The proposed algorithm introduces a pre-processing step based on the combination of Contrast Limited Adaptive Histogram Equalization (CLAHE) and Adaptive Gamma Correction Weighted Distribution (AGCWD) with a guided filter (GF). The cost value of the pre-processing step is determined in the matching cost step using the census transform (CT), which is followed by aggregation using the fixed-window and GF technique. A winner-takes-all (WTA) approach is employed to select the minimum disparity map value and final refinement using left-right consistency checking (LR) along with a weighted median filter (WMF) to remove outliers. The algorithm improved the accuracy 31.65% for all pixel errors and 23.35% for pixel errors in nonoccluded regions compared to several established algorithms on a Middlebury dataset.

Dynamic range reduction of infrared images based on adaptive equalization, stretch and compression of histogram

The problem of reducing the dynamic range and improving the quality of infrared (IR) images with a wide dynamic range for their display on a liquid crystal matrix with 8-bit pixels is considered. To solve this problem in optoelectronic devices in real time, block algorithms based on local equalization of the histogram are widely used, taking into account their relatively low computational complexity and the possibility of taking into account local features of the brightness distribution. The basic adaptive histogram equalization algorithm provides reasonably high image quality after conversion, but may result in excessive contrast for some types of images. In a modified algorithm of adaptive histogram equalization, the contrast is limited by a threshold by truncating local maxima at the edges of the histogram. This leads, however, to a deterioration in other indicators of image quality. This disadvantage is inherent in many algorithms of local histogram equalization, along with limited control over the characteristics of image reproduction quality. To improve the quality and expand the control interval for the characteristics of the reproduction of infrared images, the article proposes an algorithm for double reduction of the dynamic range of the image with intermediate control of the shape of its histogram. This algorithm performs: preliminary reduction of the dynamic range of the image based on adaptive equalization of the histogram, control of the shape of the histogram based on its linear or nonlinear compression, linear stretching of its central part and linear stretching (compression) of its lateral parts, final reduction of the dynamic range based on linear compression of the entire histograms. The characteristics of the proposed algorithm are compared with the characteristics of known algorithms for reducing the dynamic range and improving the image quality. The dependences of the characteristics of the quality of image reproduction after a decrease in their dynamic range on the control parameters of the proposed algorithm and recommendations for their choice taking into account the computational complexity are given.

PENERAPAN RANDOM FOREST UNTUK PENGENALAN JENIS IKAN BERDASARKAN PERBAIKAN CITRA CLAHE DAN DARK CHANNEL PRIOR

Ancaman terhadap kekayaan alam semakin terlihat, oleh karena itu upaya untuk melindungi populasi biota perairan sangat menantang bagi banyak negara. Upaya untuk mengatasi kerusakan terhadap populasi ikan asli telah dilakukan dengan mengurangi populasi ikan invasif melalui teknik penangkapan ikan tradisional. Namun, teknik penangkapan tersebut tidak hanya menangkap spesies ikan invasif tetapi juga spesies asli. Oleh karena itu, masih diperlukan proses manual untuk memilah hasil tangkapan sehingga menghabiskan energi dan waktu. Maka, perlu ditingkatkan kemampuan pengenalan ikan secara otomatis dengan bantuan computer. Telah ada penelitian sebelumnya untuk mengenali jenis-jenis ikan, namun tidak banyak yang mempertimbangkan adanya noice atau artefak-artefak yang timbul karena kondisi bawah air serta efek fitur-fitur ikan yang saling berkaitan. Oleh karena itu dalam penelitian ini, peneliti ini mengusulkan untuk melakukan analisis dampak pre-processing dari kombinasi algoritma CLAHE dan DCP yang diterapkan dalam klasifikasi ikan dengan Random Forest. Pre-processing yang yang diberikan bertujuan untuk mengatasi artefak atau noice yang timbul pada citra bawah air dan mengatasi efek dari fitur-fitur keragaman jenis ikan. Sehingga diharapkan mampu menghasilkan klasifikasi yang lebih baik dari penelitian sebelumnya. Klasifikasi dengan menggunakan Random Forest (RF) dengan perbaikan citra Dark Channel Prior (DCP) dan Contract Limited Adaptive Histogram Equalization (CLAHE), terbukti memberikan nilai akurasi rata-rata yang cukup tinggi yakni sebesar 98.51%, presisi 78.91%, dan recall 36.71%.

Best Regression for Eye Recognition

Human eye offers a number of opportunities for biometric recognition. The essential parts of the eye like cornea, iris, veins and retina can determine different characteristics. Systems using eyes’ features are widely deployed for identification in government requirement levels and laws; but also beginning to have more space in portable validation world. The first image was prepared to be used and monitored using CLAHE which means (Contrast Limited Adaptive Histogram Equalization) to improve the contrast of the image, after that the 3D surface plot was created for this image then different types of regression were used and the better one was chosen. The results showed that power regression is better, and fitter than other fitting methods (8th, 7th, 6th, 5th, 4th, 3rd, 2nd) degree polynomial, and straight line respectively, when depending on the sum of residual squared. The estimations of R-square demonstrated that (5th, 6th, 7th, 8th) have a great proportion of variance in the model followed by (power, 4th, 3rd, 2nd, straight line) respectively. The conclusion from these results is that the power regression has a better fitting than other types of fitting functions for this study and similar ones.

Enhancing MRI Brain Images Using Contourlet Transform and Adaptive Histogram Equalization

Human brain can be viewed using MRI images. These images will be useful for physicians, only if their quality is good. We propose a new method called, Contourlet Based Two Stage Adaptive Histogram Equalization (CBTSA), that uses Nonsubsampled Contourlet Transform (NSCT) for smoothing images and adaptive histogram equalization (AHE), under two occasions, called stages, for enhancement of the low contrast MRI images. The given MRI image is fragmented into equal sized sub-images and NSCT is applied to each of the sub-images. AHE is imposed on each resultant sub-image. All processed images are merged and AHE is applied again to the merged image. The clarity of the output image obtained by our method has outperformed the output image produced by traditional methods. The quality was measured and compared using criteria like, Entropy, Absolute Mean Brightness Error (AMBE) and Peak Signal to Noise Ratio (PSNR).

Classification of Spine Image from MRI Image Using Convolutional Neural Network

The spine tumor is a fast-growing abnormal cell in the spinal canal or vertebrae of the spine, it affected many people. Thousands of researchers have focused on this disease for better understanding of tumor classification to provide more effective treatment to the patients. The main objective of this paper is to form a methodology for classification of spine image. We proposed an efficient and effective method that helpful for classifying the spine image and identified tumor region without any human assistance. Basically, Contrast Limited Adaptive Histogram Equalization used to improve the contrast of spine images and to eliminate the effect of unwanted noise. The proposed methodology will classify spine images as Normal or Abnormal using Convolutional Neural Network (CNN) model algorithm. The CNN model can classify spine image as Normal or Abnormal with 99.4% Accuracy, 94.5% Sensitivity, 95.6% Precision, and 99.9% specificity. Compared with the previous existing methods, our proposed solution achieved the highest performance in terms of classification based on the spine dataset. From the experimental results performed on the different images, it is clear that the analysis for the spine tumor detection is fast and accurate when compared with the manual detection performed by radiologists or clinical experts, So, anyone can easily identify the tumor affected area also determine abnormal images.

Peningkatan Kualitas Citra Reduksi Noise Menggunakan Iterative Denoising and Backward Projection-CNN dan TFM-CLAHE Pada Citra 24 Bit

Penurunan kualitas yang diakibatkan adanya noise atau kontras yang tidak normal pada citra mengakibatkan objek pada citra menjadi tidak jelas. Masalah itu dapat disebabkan perangkat yang digunakan menimbulkan noise atau tidak bisa menghasilkan kontras yang normal. Adanya noise dan kontras rendah gelap berdampak besar terhadap kualitas citra?, proses reduksi noise yang berukuran besar 45% akan berpengaruh pada informasi didalam citra sehingga kualitas citra hasil reduksi menjadi hal yang perlu dipertimbangkan untuk noise berukuran besar?. Penelitian tahun 2019 menggunakan algoritma Iterative Denoising and Backward Projections with CNN (IDBP-CNN) dinyatakan mampu mereduksi noise hingga 51% dengan kualitas PSNR diatas 30 dB dengan mengabaikan kontras dari citra. Sedangkan algoritma untuk meningkatkan kontras citra menggunakan algoritma Triangular Fuzzy Membership?Contrast Limited Adaptive Histogram Equalization (TFM-CLAHE) juga diklaim mampu meningkatkan kontras citra dengan kualitas PSNR di atas 20 dB, yang lebih baik dibandingkan dengan algoritma CLAHE. Berdasarkan hasil pengujian yang dilakukan pada 10 citra kontras rendah gelap dengan noise 45% didapatkan kombinasi algoritma TFM-CLAHE diikuti IDBP-CNN lebih baik dengan rata-rata hasil PSNR = 31.69 dB, dibandingkan sebaliknya PSNR = 31.01 dB, Namun rata-rata keragaman informasi citra hasil dengan kombinasi IDBP-CNN diikuti TFM-CLAHE lebih kecil selisihnya terhadap citra asli berdasarkan Shanon Entropy sebesar 3.77% dibandingkan sebaliknya 4.75%