Film image processing and production based on high-performance calculation

Remarkable technological developments for efficient image recognition (i.e., image acquisition and image data processing) have been reported in the past decade. Such advances in imaging and image processing technologies have driven significant progress in mobile electronics and machine vision applications. In particular, for image acquisition devices, two types of natural eyes (i.e., chambered and compound eyes) have inspired the development of novel multifunctional imaging devices with unique optical geometries. For image data processing devices, novel computing devices based on memristor crossbar arrays, such as electronic synapses, have been developed. More recently, the integration of imaging and image processing devices in a single unit further enhances the system‐level efficiency. Herein, such recent advances in the bio‐inspired artificial vision and neuromorphic image processing devices, aimed at providing efficient image recognition, are reviewed. First, various imaging devices inspired by the structural and functional features of natural eyes are introduced. Second, artificial synapses and their operation principles are thoroughly discussed. Third, the neuromorphic vision sensor that integrates the imaging and image processing devices is reviewed. Finally, a brief summary and future outlook are presented.

With the rapid development of the film and television industry and the increasing prosperity of the sports industry, interdisciplinary education plays an increasingly important role in talent training. The purpose of this paper is to explore how to develop an effective talent cultivation strategy for film and television photography and production majors in the interdisciplinary context, combined with the characteristics of sports speciality students. Through in-depth analysis of the advantages and shortcomings of sports special students, combined with the actual needs of film and television photography and production majors, this paper puts forward a series of cultivation strategies, with a view to cultivating composite talents with sports literacy and film and television technology dual capabilities. Sports speciality students have good physical quality and teamwork ability, and these qualities are especially important in the process of film and television production. However, they may have deficiencies in artistic expression and technical operation. Therefore, to address this situation, this paper suggests increasing the proportion of artistic aesthetics and technical practice in the curriculum, and enhancing students' comprehensive quality through project practice and interdisciplinary cooperation. Emphasis on the combination of sports and film and television. By offering special courses such as filming of sports events and production of sports documentaries, students can gain an in-depth understanding of the operation and filming techniques of sports events while learning film and television technology. In addition, through the introduction of industry experts and off-campus practical training, students' practical operation ability and industry adaptability are enhanced. Focus on cultivating students' innovative thinking and cross-border co-operation ability. Students are encouraged to participate in interdisciplinary projects to develop their ability to solve complex problems and their sense of innovation, so as to better adapt to the development needs of the film and television industry. Through the above strategies, this paper expects to provide a more comprehensive education for sports speciality students majoring in film and television photography and production, and to cultivate high-quality composite talents with both sports literacy and proficiency in film and television technology.

Facial recognition is one of the most challenging and interesting problems within the field of computer vision and pattern recognition. During the last few years, it has gained special attention due to its importance in relation to current issues such as security, surveillance systems and forensics analysis. Despite this high level of attention to facial recognition, the success is still limited by certain conditions; there is no method which gives reliable results in all situations. In this paper, we propose an efficient similarity index that resolves the shortcomings of the existing measures of feature and structural similarity. This measure, called the Feature-Based Structural Measure (FSM), combines the best features of the well-known SSIM (structural similarity index measure) and FSIM (feature similarity index measure) approaches, striking a balance between performance for similar and dissimilar images of human faces. In addition to the statistical structural properties provided by SSIM, edge detection is incorporated in FSM as a distinctive structural feature. Its performance is tested for a wide range of PSNR (peak signal-to-noise ratio), using ORL (Olivetti Research Laboratory, now AT&T Laboratory Cambridge) and FEI (Faculty of Industrial Engineering, São Bernardo do Campo, São Paulo, Brazil) databases. The proposed measure is tested under conditions of Gaussian noise; simulation results show that the proposed FSM outperforms the well-known SSIM and FSIM approaches in its efficiency of similarity detection and recognition of human faces.

In this study, we propose a CNN-GAN-based real-time processing technique for filtering images of underwater cables used in power systems. This addresses the excessive interference impurities that are frequently observed in images captured by remotely operated vehicles (ROVs). The process begins with the input of the original image into the convolutional neural network (CNN). Subsequently, the training outcomes, which serve as input parameters for the generative adversarial network (GAN), facilitate the filtering process. The system also calculates both the structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR), performing model updates via backward propagation. This technique utilizes deep learning technologies to achieve rapid, real-time filtering of underwater cable images. The experimental results reveal that the loss function of the CNN reaches 0.16 with an accuracy of 97.5%, while the loss function of the adversarial GAN network approaches 0.05. Compared with traditional methods such as DDN, JORDOR, RESCAN, and PRENet, the proposed CNN-GAN algorithm exhibits superior performance, as evidenced by the higher PSNR and SSIM values. Specifically, for clear water images, the PSNR reaches 29.86 dB and the SSIM is 0.9045. For severely polluted images, the PSNR is 28.67 dB and the SSIM is 0.8965, while for unevenly illuminated images, the PSNR and SSIM values are 24.37 dB and 0.88, respectively. These enhancements significantly benefit the monitoring and maintenance of power systems.

With the widespread adoption of Generative Adversarial Networks (GANs) in image generation and processing, enhancing their generation quality and visualization capabilities has become a prominent research focus. This study introduces a deep learning framework that integrates multi-scale information chart generation with visualization enhancement to improve the performance of GAN-based image generation models across various domains. Based on the Self-Attention Generative Adversarial Network (SAGAN), which leverages self-attention mechanisms to capture long-range dependencies in images, the proposed approach significantly enhances image quality and detail representation. The framework incorporates a multi-scale feature extraction method to optimize the feature maps at each layer of the generative network. Experimental results demonstrate that SAGAN outperforms traditional GAN models in terms of image clarity, detail preservation, and visual effects. The proposed model achieves notable improvements in diversity and generalization, with a mutual information content of 0.91, clustering uniformity of 0.89, and inter-cluster dissimilarity of 0.92 on the CelebA dataset. Furthermore, in terms of image quality, SAGAN attains a Structural Similarity Index Measure (SSIM) of 0.94 and a Peak Signal-to-Noise Ratio (PSNR) of 30.1, surpassing traditional GANs by a significant margin.

The major studied in this dissertation is the non-destructive testing method of silkworm cocoon's quality, based on the digital image processing and photoelectricity technology. Through the images collection and the data analysis, procession and calculation of the tested silkworm cocoons with the non-destructive testing technology, internet applications automatically reckon all items of the classification indexes. Finally we can conclude the classification result and the purchase price of the silkworm cocoons. According to the domestic classification standard of the silkworm cocoons, the author investigates various testing methods of silkworm cocoons which are used or have been explored at present, and devices a non-destructive testing scheme of the silkworm cocoons based on the digital image processing and photoelectricity technology. They are dissertated about the project design of the experiment. The precisions of all the implements are demonstrated. I establish Manifold mathematic models, compare them with each other and analyze the precision with technology of databank to get the best mathematic model to figure out the weight of the dried silkworm cocoon shells. The classification methods of all the complementary items are designed well and truly. The testing method has less error and reaches an advanced level of the present domestic non-destructive testing technology of the silkworm cocoons.

Although it is a technology that can be pretty important for remote areas lacking internet or cellular data, the difficulties it presents in large data transmission prevent LoRa from developing sufficiently for image transmission. This challenge is particularly relevant for applications requiring the transfer of facial images, such as remote security or identification. It is possible to overcome these difficulties by reducing the data size through the application of various image processing methods. In the study, the face-focused enhanced super-resolution generative adversarial network (ESRGAN) is trained to address the significant quality loss in low-resolution face images transmitted to the receiver as a result of image processing techniques. Also, the trained ESRGAN model is evaluated comparatively with the Real-ESRGAN model and a standard bicubic interpolation baseline. In addition to Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics, Learned Perceptual Image Patch Similarity (LPIPS) for perceptual quality and a facial identity preservation metric are used to calculate the similarities of the produced super-resolution (SR) images to the original images. The study was tested in practice, demonstrating that a facial image transmitted in 42 min via LoRa can be transmitted in 5 s using image processing techniques and that the images can be improved close to the real images at the receiver. Thus, with an integrated system that enhances the transmitted visual data, it becomes possible to transmit compressed, low-resolution image data using LoRa. The study aims to contribute to remote security or identification studies in regions with difficult internet and cellular data transmission by making significant improvements in image transmission with LoRa.

Today, video production monitors are integral to television, broadcasting, and film production. In fact, because monitors accurately display what the camera sees without any changes or enhancements, they deliver a realistic image essential for video production. Though a camera offers a suggested exposure setting, images demand greater exposure accuracy. It is therefore essential to understand the camera’s exposure level. Underexposure shots tend to lack clarity and overexposure causes in advertent loss of detail in image’s highlights. The challenge thus is in setting the correct level of exposure to convey a message. An external monitor has certain distinguishing features that enhance picture quality in several ways. One such feature is ‘false colour’, which is found primarily on external monitors. False colour benefits cinematographers by transforming varied exposure levels in a frame into distinct bands. They are allowing the user to see where under or overexposure is occurring. It exposes faults that a built-in internal camera viewfinder may easily ignore while minimizing overheating issues. This paper undertakes a comparative analysis of the picture quality in terms of colour, brightness, and contrast of an external monitor with the camera’s inbuilt viewfinder. This is an experimental study that determines the amount and quality of exposure that an image receives. Furthermore, this research experiments with ‘false colour’ viewing in terms of the IRE value chart and examines the exposure levels of all parts of the shots before recording. In this research, a stunning and perfectly exposed image was made by adjusting the false colours according to the IRE value. Underexposed areas appeared in blue, and overexposed areas in red. Checking on the skin tones faster is the key to exposing the image quickly and accurately with the help of false colour.

InfraGAN: A GAN architecture to transfer visible images to infrared domain

PurposeThe purpose of this study was to evaluate the accuracy and perceptual quality of red-green-blue (RGB) fundus images generated from red-green (RG) images using Pix2Pix-based generative adversarial network (GAN).MethodsRG images were extracted from original RGB images recorded by a newer model of the Optos system by turning off the blue laser source. A conditional GAN based on the Pix2Pix architecture was trained to convert this extracted RG image to an RGB image. The performance was evaluated quantitatively by using a five-fold cross-validation and assessments with structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), learned perceptual image patch similarity (LPIPS), mean absolute error (MAE), and root mean square error (RMSE). To assess the perceptual accuracy, 39 ophthalmologists examined 60 randomly selected images, 30 true and 30 generated RGB images, using Google Form-based interface. They were instructed to classify each image as a true or an artificial intelligence (AI)-generated image.ResultsThe generated images had high similarity to the original RGB images (SSIM = 0.97 ± 0.00; PSNR = 35.74 ± 0.17 decibel [dB]; LPIPS = 0.09 ± 0.00; MAE = 1.76 ± 0.04; and RMSE = 4.25 ± 0.10). The overall correct classification rate was 57.1%. Certain lesion types, such as epiretinal membrane and optic disc cupping, had higher discrimination rates. The receiver operating characteristic (ROC) analysis across all evaluations yielded an area under the curve (AUC) of 0.497 (P = 0.314).ConclusionsPix2Pix-based GANs can generate perceptually and structurally consistent RGB images from RG images without lesion-specific attention mechanisms.Translational RelevanceThis method enables a reinterpretation of legacy RG fundus images and may support future AI diagnostic applications.

Robust structural similarity index measure for images with non-Gaussian distortions

Aim: Image is the most powerful tool to analyze the information. Sometimes the captured image gets affected with blur and noise in the environment, which degrades the quality of the image. Image restoration is a technique in image processing where the degraded image can be restored or recovered to its nearest original image. Materials and Methods: In this research Lucy-Richardson algorithm is used for restoring blurred and noisy images using MATLAB software. And the proposed work is compared with Wiener filter, and the sample size for each group is 30. Results: The performance was compared based on three parameters, Power Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Normalized Correlation (NC). High values of PSNR, SSIM and NC indicate the better performance of restoration algorithms. Lucy-Richardson provides a mean PSNR of 10.4086db, mean SSIM of 0.4173%, and NC of 0.7433% and Wiener filter provides a mean PSNR of 6.3979db, SSIM of 0.3016%, NC of 0.3276%. Conclusion: Based on the experimental results and statistical analysis using independent sample T test, image restoration using Lucy-Richardson algorithm significantly performs better than Wiener filter on restoring the degraded image with PSNR (P<0.001) and SSIM (P<0.001).

The digital image acquisition and processing technology already mature also in domains and so on visual communication obtains day by day[1]. However, the image acquisition and processing technology had many kinds, for example white balance processing and image denoising methods. The traditional image acquisition and processing systems are implemented using software by the PC or DSP chip[2], and sometimes software in series can not meet the requirement of high speed image processing. this article has given FPGA in the image acquisition and processing simple application, applied FPGA in the image acquisition and processing to be possible to enhance the image processing the speed, reduced takes the logical unit. The system designed by above-mentioned way achieves a satisfying effect by experimental verification.

Image dehazing has always been a challenging topic in image processing. The development of deep learning methods, especially the generative adversarial networks (GAN), provides a new way for image dehazing. In recent years, many deep learning methods based on GAN have been applied to image dehazing. However, GAN has two problems in image dehazing. Firstly, For haze image, haze not only reduces the quality of the image but also blurs the details of the image. For GAN network, it is difficult for the generator to restore the details of the whole image while removing the haze. Secondly, GAN model is defined as a minimax problem, which weakens the loss function. It is difficult to distinguish whether GAN is making progress in the training process. Therefore, we propose a guided generative adversarial dehazing network (GGADN). Different from other generation adversarial networks, GGADN adds a guided module on the generator. The guided module verifies the network of each layer of the generator. At the same time, the details of the map generated by each layer are strengthened. Network training is based on the pre-trained VGG feature model and L1-regularized gradient prior which is developed by new loss function parameters. From the dehazing results of synthetic images and real images, the proposed method is better than the state-of-the-art dehazing methods.

In general, monitoring of animal growth and health is done directly by farmers (invasive measurement methods) which can cause cows to be injured or experience stress. To avoid this, several studies have been conducted on non-invasive methods using image processing technology. In this study, we systematically reviewed several works of literature to identify and synthesize published articles on image processing technology and image processing applications related to weight estimation and individual cattle identification. Analysis of image processing technologies used for weight estimation and individual cattle identification is the main objective of this article. Articles were searched through several databases and studies that met the inclusion criteria were analyzed and used in the review. The studies were divided into three main themes: image processing technologies, applications using image processing, and image processing research on cattle growth and health. It can be concluded that deep learning approaches are increasingly being studied, tested and considered as a viable and promising approach to monitor cattle weight and health in several aspects