Image Life Trails Based On Contrast Reduction Models For Face Counter-Spoofing

Natural face images are both content and context-rich, in the sense that they carry significant immersive information via depth cues embedded in the form of self-shadows or a space varying blur. Images of planar face prints, on the other hand, tend to have lower contrast and also suppressed depth cues. In this work, a solution is proposed, to detect planar print spoofing by enhancing self-shadow patterns present in face images. This process is facilitated and siphoned via the application of a non-linear iterative functional map, which is used to produce a contrast reductionist image sequence, termed as an image life trail. Subsequent images in this trail tend to have lower contrast in relation to the previous iteration. Differences taken across this image sequence help in bringing out the self-shadows already present in the original image. On a client specific mode, when the subjects and faces are registered, secondary statistics which capture the prominence of self-shadow information, indicate that planar print-images tend to have highly suppressed self-shadows when compared with natural face images. An elaborate tuning procedure, based on a reduced set of training images was developed to first identify the optimal parameter set and then adapt the feature-vectors so that the error-rates were minimized for a specific dataset. Overall mean error rate for the calibration-set (reduced CASIA dataset) was found to be 0.267% and the error rates for other datasets such OULU-NPU and CASIA-SURF were 0.17% and 0.73% respectively

Counting using deep learning regression gives value to ecological surveys

Many ecological studies rely on count data and involve manual counting of objects of interest, which is time-consuming and especially disadvantageous when time in the field or lab is limited. However, an increasing number of works uses digital imagery, which opens opportunities to automatise counting tasks. In this study, we use machine learning to automate counting objects of interest without the need to label individual objects. By leveraging already existing image-level annotations, this approach can also give value to historical data that were collected and annotated over longer time series (typical for many ecological studies), without the aim of deep learning applications. We demonstrate deep learning regression on two fundamentally different counting tasks: (i) daily growth rings from microscopic images of fish otolith (i.e., hearing stone) and (ii) hauled out seals from highly variable aerial imagery. In the otolith images, our deep learning-based regressor yields an RMSE of 3.40 day-rings and an $$R^2$$ R 2 of 0.92. Initial performance in the seal images is lower (RMSE of 23.46 seals and $$R^2$$ R 2 of 0.72), which can be attributed to a lack of images with a high number of seals in the initial training set, compared to the test set. We then show how to improve performance substantially (RMSE of 19.03 seals and $$R^2$$ R 2 of 0.77) by carefully selecting and relabelling just 100 additional training images based on initial model prediction discrepancy. The regression-based approach used here returns accurate counts ($$R^2$$ R 2 of 0.92 and 0.77 for the rings and seals, respectively), directly usable in ecological research.

Filtering Random Valued Impulse Noise from Grayscale Images through Support Vector Machine and Markov Chain

This paper presents a context-based filter to denoise grayscale images affected by random valued impulse noise. A support vector machine classifier is used for noise detection and two Markov filter variants are evaluated for their denoising capacity. The classifier needs to be trained on a set of training images. The experiments performed on another set of test images have shown that the support vector machine with the radial basis function kernel combined with the Markov+ filter is the best configuration, providing the highest noise detection accuracy. Our filter was compared with existing denoising methods, it being better on some images and comparable with them on others.

IDENTIFIKASI CITRA BATIK DENGAN METODE CONVOLUTIONAL NEURAL NETWORK

Batik merupakan suatu kerjianan tangan yang memiliki nilai seni yang cukup tinggi dan juga salah satu bagian dari budaya indonessia. Untuk melestraikan budaya warisan batik dapat dikakukan dengan berbagai cara dengan pengenalan pola batik yang sangat beragam khususnya batik karawang. Penelitian ini membahas klasifikasi pola batik karawang menggunakan Convolutional Neural Network (CNN) dengan ciri gray level Co-ocurrence Matrix. Proses awal yang akan dilakukan yaitu preprocessing untuk mengubah citra warna menjadi grayscale, selanjutnya citra akan di segmentasikan sehingga memisahkan citra pola batik dengan background menggunakan metode otsu dan di ekstraksi menggunakan metode gray level co-ocurrence matrix untuk mendeteksi pola-pola batik. selanjutnya akan diklasifikasikan menggunakan metode Convolutional Neural Network (CNN) yang memberikan hasil klasifikasi citra batik. Dengan penerapan model klasifikasi citra batik Karawang ini memliki data training sebanyak 1094 citra latih dengan nilai akurasi 18,19% untuk citra latih, citra dapat mengklasifikasikan dengan uji coba 344 citra batik, 45 citra batik Karawang, 299 citra batik luar Karawang mencapai 18,60% nilai tingkat akurasi, sedangkan hasil uji coba menggunakan citra batik karawang yang dapat dikenali dan diklasifikasikan mencapai nilai tingkat akurasi 73,33 %. Kata Kunci : Klasifikasi citra batik, CNN, GLCM, Otsu, Image Processing Batik is a handicraft that has a high artistic value and also Batik is a part of Indonesian culture. To preserve the cultural heritage of batik it can be do in various ways with the introduction of many diverse batik patterns, especially karawang batik.. This study discusses the classification of Karawang batik patterns using Convolutional Neural Network (CNN) with gray level co-occurrence matrix characteristics. Initial process is preprocessing to convert the color image to grayscale, Then the image will be segmented. It can separated the image of the batik pattern from the background using the Otsu method and extracted using the gray level co-occurrence matrix method to detect batik patterns. Then, it will be classified using the Convolutional Neural Network (CNN) method which gives the results of batik image classification. With the application of this Karawang batik image classification model, it has training data of 1094 training images with an accuracy value of 18.19% for training images, images can be classified by testing 344 batik images, 45 Karawang batik images, 299 outer Karawang batik images reaching 18.60 % the value of the accuracy level, while the results of the trial using the image of batik karawang which can be recognized and classified reach an accuracy level of 73.33%. Keywords: Batik image classification, CNN, GLCM, Otsu, Image Processing

Image emotion distribution learning based on enhanced fuzzy KNN algorithm with sparse learning

With the trend of people expressing opinions and emotions via images online, increasing attention has been paid to affective analysis of visual content. Traditional image affective analysis mainly focuses on single-label classification, but an image usually evokes multiple emotions. To this end, emotion distribution learning is proposed to describe emotions more explicitly. However, most current studies ignore the ambiguity included in emotions and the elusive correlations with complex visual features. Considering that emotions evoked by images are delivered through various visual features, and each feature in the image may have multiple emotion attributes, this paper develops a novel model that extracts multiple features and proposes an enhanced fuzzy k-nearest neighbor (EFKNN) to calculate the fuzzy emotional memberships. Specifically, the multiple visual features are converted into fuzzy emotional memberships of each feature belonging to emotion classes, which can be regarded as an intermediate representation to bridge the affective gap. Then, the fuzzy emotional memberships are fed into a fully connected neural network to learn the relationships between the fuzzy memberships and image emotion distributions. To obtain the fuzzy memberships of test images, a novel sparse learning method is introduced by learning the combination coefficients of test images and training images. Extensive experimental results on several datasets verify the superiority of our proposed approach for emotion distribution learning of images.

Deep Vision for Breast Cancer Classification and Segmentation

(1) Background: Female breast cancer diagnoses odds have increased from 11:1 in 1975 to 8:1 today. Mammography false positive rates (FPR) are associated with overdiagnoses and overtreatment, while false negative rates (FNR) increase morbidity and mortality. (2) Methods: Deep vision supervised learning classifies 299 × 299 pixel de-noised mammography images as negative or non-negative using models built on 55,890 pre-processed training images and applied to 15,364 unseen test images. A small image representation from the fitted training model is returned to evaluate the portion of the loss function gradient with respect to the image that maximizes the classification probability. This gradient is then re-mapped back to the original images, highlighting the areas of the original image that are most influential for classification (perhaps masses or boundary areas). (3) Results: initial classification results were 97% accurate, 99% specific, and 83% sensitive. Gradient techniques for unsupervised region of interest mapping identified areas most associated with the classification results clearly on positive mammograms and might be used to support clinician analysis. (4) Conclusions: deep vision techniques hold promise for addressing the overdiagnoses and treatment, underdiagnoses, and automated region of interest identification on mammography.

Deep Learning Enabled Deblurring of Computed Tomography Images of Porous Media

Computed tomography (CT) is an important tool to characterize rock samples allowing quantification of physical properties in 3D and 4D. The accuracy of a property delineated from CT data is strongly correlated with the CT image quality. In general, high-quality, lower noise CT Images mandate greater exposure times. With increasing exposure time, however, more wear is put on the X-Ray tube and longer cooldown periods are required, inevitably limiting the temporal resolution of the particular phenomena under investigation. In this work, we propose a deep convolutional neural network (DCNN) based approach to improve the quality of images collected during reduced exposure time scans. First, we convolve long exposure time images from medical CT scanner with a blur kernel to mimic the degradation caused because of reduced exposure time scanning. Subsequently, utilizing the high- and low-quality scan stacks, we train a DCNN. The trained network enables us to restore any low-quality scan for which high-quality reference is not available. Furthermore, we investigate several factors affecting the DCNN performance such as the number of training images, transfer learning strategies, and loss functions. The results indicate that the number of training images is an important factor since the predictive capability of the DCNN improves as the number of training images increases. We illustrate, however, that the requirement for a large training dataset can be reduced by exploiting transfer learning. In addition, training the DCNN on mean squared error (MSE) as a loss function outperforms both mean absolute error (MAE) and Peak signal-to-noise ratio (PSNR) loss functions with respect to image quality metrics. The presented approach enables the prediction of high-quality images from low exposure CT images. Consequently, this allows for continued scanning without the need for X-Ray tube to cool down, thereby maximizing the temporal resolution. This is of particular value for any core flood experiment seeking to capture the underlying dynamics.

Super-Resolved Recognition of License Plate Characters

Object detection and recognition are crucial in the field of computer vision and are an active area of research. However, in actual object recognition processes, recognition accuracy is often degraded due to resolution mismatches between training and test image data. To solve this problem, we designed and developed an integrated object recognition and super-resolution framework by proposing an image super-resolution technique that improves object recognition accuracy. In detail, we collected a number of license plate training images through web-crawling and artificial data generation, and the image super-resolution artificial neural network was trained by defining an objective function to be robust to image flips. To verify the performance of the proposed algorithm, we experimented with the trained image super-resolution and recognition on representative test images and confirmed that the proposed super-resolution technique improves the accuracy of character recognition. For character recognition with the 4× magnification, the proposed method remarkably increased the mean average precision by 49.94% compared to the existing state-of-the-art method.