Picture-wise just noticeable difference prediction model for JPEG image quality assessment

Introduction/purpose: The paper presents interesting research related to the performance analysis of the picture-wise just noticeable difference (JND) prediction model and its application in the quality assessment of images with JPEG compression. Methods: The performance analysis of the JND model was conducted in an indirect way by using the publicly available results of subject-rated image datasets with the separation of images into two classes (above and below the threshold of visible differences). In the performance analysis of the JND prediction model and image quality assessment, five image datasets were used, four of which come from the visible wavelength range, and one dataset is intended for remote sensing and surveillance with images from the infrared part of the electromagnetic spectrum. Results: The pap 86 er shows that using a picture-wise JND model, subjective image quality assessment scores can be estimated with better accuracy, leading to significant performance improvements of the traditional peak signal-to-noise ratio (PSNR). The gain achieved by introducing the picture-wise JND model in the objective assessment depends on the chosen dataset and the results of the initial simple to compute PSNR measure, and it was obtained on all five datasets. The mean linear correlation coefficient (for five datasets) between subjective and PSNR objective quality estimates increased from 74% (traditional PSNR) to 90% (picture-wise JND PSNR). Conclusion: Further improvement of the JND-based objective measure can be obtained by improving the picture-wise model of JND prediction.

Scene terrain classification for autonomous vehicle navigation based on semantic segmentation method

Autonomous transportation is a new paradigm of an Industry 5.0 cyber-physical system that provides a lot of opportunities in smart logistics applications. The safety and reliability of deep learning-driven systems are still a question under research. The safety of an autonomous guided vehicle is dependent on the proper selection of sensors and the transmission of reflex data. Several academics worked on sensor-based difficulties by developing a sensor correction system and fine-tuning algorithms to regulate the system’s efficiency and precision. In this paper, the introduction of vision sensor and its scene terrain classification using a deep learning algorithm is performed with proposed datasets during sensor failure conditions. The proposed classification technique is to identify the mobile robot obstacle and obstacle-free path for smart logistic vehicle application. To analyze the information from the acquired image datasets, the proposed classification algorithm employs segmentation techniques. The analysis of proposed dataset is validated with U-shaped convolutional network (U-Net) architecture and region-based convolutional neural network (Mask R-CNN) architecture model. Based on the results, the selection of 1400 raw image datasets is trained and validated using semantic segmentation classifier models. For various terrain dataset clusters, the Mask R-CNN classifier model method has the highest model accuracy of 93%, that is, 23% higher than the U-Net classifier model algorithm, which has the lowest model accuracy nearly 70%. As a result, the suggested Mask R-CNN technique has a significant potential of being used in autonomous vehicle applications.

Screening Referable Diabetic Retinopathy Using a Semi-automated Deep Learning Algorithm Assisted Approach

Purpose: To assess the accuracy and efficacy of a semi-automated deep learning algorithm (DLA) assisted approach to detect vision-threatening diabetic retinopathy (DR).Methods: We developed a two-step semi-automated DLA-assisted approach to grade fundus photographs for vision-threatening referable DR. Study images were obtained from the Lingtou Cohort Study, and captured at participant enrollment in 2009–2010 (“baseline images”) and annual follow-up between 2011 and 2017. To begin, a validated DLA automatically graded baseline images for referable DR and classified them as positive, negative, or ungradable. Following, each positive image, all other available images from patients who had a positive image, and a 5% random sample of all negative images were selected and regraded by trained human graders. A reference standard diagnosis was assigned once all graders achieved consistent grading outcomes or with a senior ophthalmologist's final diagnosis. The semi-automated DLA assisted approach combined initial DLA screening and subsequent human grading for images identified as high-risk. This approach was further validated within the follow-up image datasets and its time and economic costs evaluated against fully human grading.Results: For evaluation of baseline images, a total of 33,115 images were included and automatically graded by the DLA. 2,604 images (480 positive results, 624 available other images from participants with a positive result, and 1500 random negative samples) were selected and regraded by graders. The DLA achieved an area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy of 0.953, 0.970, 0.879, and 88.6%, respectively. In further validation within the follow-up image datasets, a total of 88,363 images were graded using this semi-automated approach and human grading was performed on 8975 selected images. The DLA achieved an AUC, sensitivity, and specificity of 0.914, 0.852, 0.853, respectively. Compared against fully human grading, the semi-automated DLA-assisted approach achieved an estimated 75.6% time and 90.1% economic cost saving.Conclusions: The DLA described in this study was able to achieve high accuracy, sensitivity, and specificity in grading fundus images for referable DR. Validated against long-term follow-up datasets, a semi-automated DLA-assisted approach was able to accurately identify suspect cases, and minimize misdiagnosis whilst balancing safety, time, and economic cost.

PENGENALAN AKTIVITAS MANUSIA DAN PEMBUATAN LOG OTOMATIS DARI REKAMAN VIDEO MENGGUNAKAN MULTILAYER PERCEPTRON

Advances in technology have made it easier to surveillance purpose by installing recording equipment that can be placed in certain strategic locations. The existence of this technology also brings changes in the analysis phase of video recordings and images that have been obtained. The processing of recorded videos no longer uses manual methods but can be done automatically using image processing and artificial intelligence algorithms. Based on the obtained video recordings, analysis can be carried out for surveillance purpose, object tracking, human activity recognition, etc. This paper discusses the development of an automatic human activity recognition system based on video recordings using Multilayer Perceptron method. The recorded video will be transformed into a collection of images which are then processed with the Multilayer Perceptron algorithm for the recognition process. The output of the designed system is the recognition of activities carried out by humans at a certain time and saved them in a log with a certain timestamp. In this paper, there are five types of human activities that can be recognized automatically by the system, namely raising hands, clapping, standing, sitting, and studying. The experimental results show that the accuracy rate of the proposed system achieved 97.45% for image datasets obtained freely from the internet, while 100% accuracy was obtained for image datasets collected with IP Cameras. Keywords: Human activity recognition; video recording; Multilayer PerceptronAbstrakKemajuan teknologi memungkinkan kegiatan pengawasan terhadap lingkungan menjadi lebih mudah yaitu dengan melakukan pemasangan peralatan rekam yang dapat ditempatkan pada lokasi-lokasi strategis tertentu. Keberadaan peralatan teknologi ini juga membawa perubahan dalam proses analisis terhadap rekaman video maupun gambar yang telah didapatkan. Proses pengolahan terhadap video rekaman tidak lagi menggunakan cara manual, namun dapat dilakukan secara otomatis dengan menggunakan teknologi pengolahan citra dan kecerdasan buatan. Berdasarkan rekaman video maupun gambar yang diperoleh, analisis dapat dilakukan untuk mengawasi keamanan lokasi, mencatat perubahan kondisi objek tertentu, mengenali aktivitas manusia pada saat tertentu, dan lain sebagainya. Makalah ini membahas pengembangan sebuah sistem pengenalan aktivitas manusia secara otomatis berdasarkan rekaman video menggunakan metode Multilayer Perceptron. Rekaman video sebelumnya akan dicacah menjadi kumpulan citra yang kemudian diproses dengan algoritma Multilayer Perceptron untuk proses pengenalannya. Luaran dari sistem aplikasi yang dirancang berupa pengenalan aktivitas yang dilakukan manusia pada waktu tertentu dan pencatatan aktivitas tersebut dalam sebuah log dengan timestamp tertentu. Dalam makalah ini, terdapat lima jenis aktivitas manusia yang dapat dikenali secara otomatis oleh sistem, yaitu mengangkat tangan, bertepuk tangan, berdiri, duduk, dan belajar. Hasil pengujian menunjukkan bahwa keberhasilan pendeteksian aktivitas manusia dengan metode Multilayer Perceptron memiliki tingkat akurasi 97.45% untuk dataset citra yang diperoleh secara bebas dari internet, sedangkan untuk dataset citra yang dikumpulkan dengan IP Camera memiliki tingkat akurasi sebesar 100%.

Blind Image Separation Method Based on Cascade Generative Adversarial Networks

To solve the challenge of single-channel blind image separation (BIS) caused by unknown prior knowledge during the separation process, we propose a BIS method based on cascaded generative adversarial networks (GANs). To ensure that the proposed method can perform well in different scenarios and to address the problem of an insufficient number of training samples, a synthetic network is added to the separation network. This method is composed of two GANs: a U-shaped GAN (UGAN), which is used to learn image synthesis, and a pixel-to-attention GAN (PAGAN), which is used to learn image separation. The two networks jointly complete the task of image separation. UGAN uses the unpaired mixed image and the unmixed image to learn the mixing style, thereby generating an image with the “true” mixing characteristics which addresses the problem of an insufficient number of training samples for the PAGAN. A self-attention mechanism is added to the PAGAN to quickly extract important features from the image data. The experimental results show that the proposed method achieves good results on both synthetic image datasets and real remote sensing image datasets. Moreover, it can be used for image separation in different scenarios which lack prior knowledge and training samples.

FeatSet: A Compilation of Visual Features Extracted from Public Image Datasets

In this paper, we present FeatSet, a compilation of visual features extracted from open image datasets reported in the literature. FeatSet has a collection of 11 visual features, consisting of color, texture, and shape representations of the images acquired from 13 datasets. We organized the available features in a standard collection, including the available metadata and labels, when available. We also provide a description of the domain of each dataset included in our collection, with visual analysis using Multidimensional Scaling (MDS) and Principal Components Analysis (PCA) methods. FeatSet is recommended for supervised and non-supervised learning, also widely supporting Content-Based Image Retrieval (CBIR) applications and complex data indexing using Metric Access Methods (MAMs).