ResNET50-Based Model Combination Optimization for Anime Image Recognition

This research aims to study the deep learning applications in image recognition and classification tasks. The advantages and limitations of deep learning are explored by analysing existing deep learning algorithms and their applications on tasks such as using images to do classification, image segmentation, and target detection. In the experimental part, this paper evaluates the performance of deep learning in image recognition by using classical neural network models, including training and testing models on a large size of image datasets. The results show that neural network has good classification and detection capabilities in image recognition tasks and also achieves good results for image segmentation tasks. However, the model training process of shallow neural network models is time-consuming and performs poorly for small-scale datasets. Based on these situations, this paper proposes some optimization strategies to achieve high performance and efficiency of neural networks in image recognition and analyze the performance differences between different strategies .

Background: The accurate classification between malignant and benign breast lesions detected on mammograms is a crucial but difficult challenge for reducing false-positive recall rates and improving the efficacy of breast cancer screening. Objective: This study aims to optimize a new deep transfer learning model by implementing a novel attention mechanism in order to improve the accuracy of breast lesion classification. Methods: ResNet50 is selected as the base model to develop a new deep transfer learning model. To enhance the accuracy of breast lesion classification, we propose adding a convolutional block attention module (CBAM) to the standard ResNet50 model and optimizing a new model for this task. We assembled a large dataset with 4280 mammograms depicting suspicious soft-tissue mass-type lesions. A region of interest (ROI) is extracted from each image based on lesion center. Among them, 2480 and 1800 ROIs depict verified benign and malignant lesions, respectively. The image dataset is randomly split into two subsets with a ratio of 9:1 five times to train and test two ResNet50 models with and without using CBAM. Results: Using the area under ROC curve (AUC) as an evaluation index, the new CBAM-based ResNet50 model yields AUC = 0.866 ± 0.015, which is significantly higher than that obtained by the standard ResNet50 model (AUC = 0.772 ± 0.008) (p < 0.01). Conclusion: This study demonstrates that although deep transfer learning technology attracted broad research interest in medical-imaging informatic fields, adding a new attention mechanism to optimize deep transfer learning models for specific application tasks can play an important role in further improving model performances.

Text recognition in images is a very urgent problem in modern search engines. There are many different methods and techniques for text recognition. The paper is a method for text recognition in a standardized image. Standardized image means an image that has the same font, character size, certain writing order, such as the serial number or license plate of the car.In the paper, we developed an improved method for text recognition in the image. The method consists in a preliminary search of the same characters and memorizing their positions. Identical symbols are recognized only once. After recognition, symbols are arranged in the desired position. Image processing and isolation of character boundaries is performed using JavaCV.The modified method was developed based on the template method. Both methods were implemented in Java language. To create a text-recognition software, a neural network based on a single-layer perceptron was built. The results of tests have shown the superiority of the modified method compared to the original one. At best, the performance of the modified method is 300% of the performance of the original one. At worst, it is slower only by 5-10%. In addition, the modified algorithm requires 3 times fewer iterations.The modified algorithm allows to accelerate the text recognition process in standardized images if they have recurring characters.

Now days reading words from an unconstrained and noisy image is not easy. Text localization and recognition in an image is a research area which takes efforts to develop a computer system with an ability to automatically read the text from images. The Optical Character Recognition (OCR) tool gives good results obtained to read the text from an image. The objective of this study is to propose a new method for text localization and recognition in natural scene images with complex background. In this paper, a hybrid methodology is suggested which extracts text from natural scene image with chaotic backgrounds. The proposed approach involves four stages. First, superimposed text regions in an image are extracted based on character descriptors features like Area, Bounding box, Perimeter, Euler number, Horizontal crossings. In the second step, superimposed text regions are tested for text content or nontext using character descriptors and SVM classifier. In the third step, detection of multiple lines in localized text regions is done and line segmentation is performed using horizontal profiles. In the final step, using vertical profiles each character of the segmented line is extracted. The workout has been done using images drawn from ICDAR 2013 and SVT 2010 datasets. The results demonstrate the effectiveness of the proposed method, which can be used as an efficient method for text localization and recognition in natural scene images.

Scene texts refer to arbitrary text found in images captured by cameras in real-world settings. The tasks of text detection and recognition are critical components of computer vision, with applications spanning scene understanding, information retrieval, robotics, and autonomous driving. Despite significant advancements in deep learning methods, achieving accurate text detection and recognition in complex images remains a formidable challenge for robust real-world applications. Several factors contribute to these challenges. First, the diversity of text shapes, fonts, colors, and styles complicates detection efforts. Second, the myriad combinations of characters, often with unstable attributes, make complete detection difficult, especially when background interruptions obscure character strokes and shapes. Finally, effective coordination of multiple sub-tasks in end-to-end learning is essential for success. This research aimed to tackle these challenges by enhancing text discriminative representation. This study focused on two interconnected problems: Scene Text Recognition (STR), which involves recognizing text from scene images, and Scene Text Detection (STD), which entails simultaneously detecting and recognizing multiple texts within those images. This research focuses on implementing and evaluating the Efficient and Accurate Scene Text Detector (EAST) algorithm for text detection and recognition in natural scene images. The study aims to compare the performance of three prominent Optical Character Recognition (OCR) techniques—TesseractOCR, PaddleOCR, and EasyOCR. The EAST model was applied to a series of sample test images, and the results were visually represented with bounding boxes highlighting the detected text regions. The inference times for each image were recorded, highlighting the algorithm's efficiency, with average times of 0.446, 0.439, and 0.440 seconds for the respective test images. These results indicate that the EAST algorithm is accurate and operates in real-time, making it suitable for applications requiring immediate text recognition.

Corrigendum to ‘Deep learning improves taphonomic resolution: high accuracy in differentiating tooth marks made by lions and jaguars'

In recent years Neural Networks and especially Deep Neural Networks (DNN) have seen a rise in popularity. DNNs have increased the overall performance of algorithms in applications such as image recognition and classification, 2D and 3D pose detection, natural language processing, and time series forecasting. Especially in image classification and recognition, so-called Convolutional Neural Network (CNN) have gained high interest as they can reach a high accuracy, which makes them a viable solution in cancer detection or autonomous driving. As CNNs are widely used in image tasks, different visualizations techniques have bee developed to show how their internals are working. Apart from image tasks, CNNs are applicable to other problems, e.g., time series classification, time series forecasting, or natural language processing. CNNs in those contexts behave similarly, allowing for the same visualization techniques to make them more interpretable. In this chapter, we adapt image visualization algorithms to time series problems, allowing us to build granular, intuitively interpretable feature hierarchies to make a time series forecast as understandable as an image recognition task. We do so by using our previous work on power time series forecasting using CNN Auto Encoders (AEs) and applying typical CNN visualization techniques to it. Thus, we guid computer scientists to provide better interpretable figures for a time series forecasting task to application domain experts.KeywordsVisualizationConvolutional neural networksTime series data

A new image recognition system based on multiple linear regression is proposed. Particularly, there are a number of innovations in image segmentation and recognition system. In image segmentation, an improved histogram segmentation method which can calculate threshold automatically and accurately is proposed. Meanwhile, the regional growth method and true color image processing are combined with this system to improve the accuracy and intelligence. While creating the recognition system, multiple linear regression and image feature extraction are utilized. After evaluating the results of different image training libraries, the system is proved to have effective image recognition ability, high precision, and reliability.

Reservoir computing has attracted much attention for its easy training process as well as its ability to deal with temporal data. A reservoir computing system consists of a reservoir part represented as a sparsely connected recurrent neural network and a readout part represented as a simple regression model. In machine learning tasks, the reservoir part is fixed and only the readout part is trained. Although reservoir computing has been mainly applied to time series prediction and recognition, it can be applied to image recognition as well by considering an image data as a sequence of pixel values. However, to achieve a high performance in image recognition with raw image data, a large-scale reservoir including a large number of neurons is required. This is a bottleneck in terms of computer memory and computational cost. To overcome this bottleneck, we propose a new method which combines reservoir computing with untrained convolutional neural networks. We use an untrained convolutional neural network to transform raw image data into a set of smaller feature maps in a preprocessing step of the reservoir computing. We demonstrate that our method achieves a high classification accuracy in an image recognition task with a much smaller number of trainable parameters compared with a previous study.

Uyghur text detection and recognition in images with simple backgrounds is still a challenging task for Uyghur image content analysis. In this paper, we propose a new effective Uyghur text detection method based on channel-enhanced MSERs and the CNN classification model. In order to extract more complete text components, a new text candidate region extraction algorithm is put forward, which is based on the channel-enhanced MSERs according to the characteristics of Uyghur text. In order to effectively prune the non-text regions, we design a CNN classification network according to the LeNet-5, which gains the description characteristics automatically and avoids the tedious and low efficiency artificial characteristic extraction work. For Uyghur text recognition in images, we improved the traditional CRNN network, and to verify its effectiveness, the networks trained on a synthetic dataset and evaluated on the text recognition datasets. The experimental results indicated that the Uyghur text detection method in this paper is robust and applicable, and the recognition result by improvedCRNN was better than the original CRNN network.

To capture and analyze the motion state of patients in real time and improve the evaluation effect of sports injury, the research is based on image recognition in visual image capture technology. Firstly, multiscale attention mechanism was introduced into U-Net image segmentation model to improve the pre-processing of image recognition. Then, the image recognition model of convolutional neural network is optimized by gradient class weighted activation mapping. The combination of the two is applied to the sports injury image processing to verify the effect. The results show that the F1 score and Precision values of the improved segmentation model in the database reach 98.85% and 98.74%, respectively. The segmentation accuracy is obviously improved. The accuracy of the optimized image recognition method in the training set and the test set is about 96% and 98%, respectively. After the combination of the two methods, the processing accuracy of sports injury medical images is 97%, and the running time is within 4s. It has high accuracy and processing efficiency, providing a technical and methodological basis for sports injury rehabilitation training.

Mobile Augmented Reality (AR), which overlays digital content on the real-world scenes surrounding a user, is bringing immersive interactive experiences where the real and virtual worlds are tightly coupled. To enable seamless and precise AR experiences, an image recognition system that can accurately recognize the object in the camera view with low system latency is required. However, due to the pervasiveness and severity of image distortions, an effective and robust image recognition solution for “in the wild” mobile AR is still elusive. In this article, we present CollabAR, an edge-assisted system that provides distortion-tolerant image recognition for mobile AR with imperceptible system latency . CollabAR incorporates both distortion-tolerant and collaborative image recognition modules in its design. The former enables distortion-adaptive image recognition to improve the robustness against image distortions, while the latter exploits the spatial-temporal correlation among mobile AR users to improve recognition accuracy. Moreover, as it is difficult to collect a large-scale image distortion dataset, we propose a Cycle-Consistent Generative Adversarial Network-based data augmentation method to synthesize realistic image distortion. Our evaluation demonstrates that CollabAR achieves over 85% recognition accuracy for “in the wild” images with severe distortions, while reducing the end-to-end system latency to as low as 18.2 ms.

At present, in medical diagnosis, facial acne vulgaris is a common disease, which mainly occurs in adolescents and has a large population base. For different degrees of facial acne, it needs to be classified and treated to relieve the pressure on medical resources. Normally, dermatologists use models that artificially determine the severity of acne vulgaris on the face. However, the outstanding problem is that it is a waste of manpower, and it may not be possible to quickly and reasonably grade acne treatment of different degrees. In this article, in view of the above problems, image recognition is used to judge the severity of facial acne vulgaris at different levels, so that perform hierarchical diagnosis and treatment. Therefore, this paper designs a graded diagnosis and treatment system for facial acne vulgaris based on image recognition. The system includes a camera acquisition system, an image processing system, an image recognition system, and related detection algorithms. In the processing process, the collected facial acne vulgaris images are mainly subjected to color processing, image segmentation processing and contour detection, and combined with Harris corner detection algorithm to detect acne. In order to determine the severity of acne and the site of the disease to a certain extent, and provide a reference for graded diagnosis and treatment.

To prevent needlestick injury and leftover instruments, and to perform efficient dental treatment, it is important to know the instruments required during dental treatment. Therefore, we will obtain a dataset for image recognition of dental treatment instruments, develop a system for detecting dental treatment instruments during treatment by image recognition, and evaluate the performance of the system to establish a method for detecting instruments during treatment. We created an image recognition dataset using 23 types of instruments commonly used in the Department of Restorative Dentistry and Endodontology at Osaka University Dental Hospital and a surgeon’s hands as detection targets. Two types of datasets were created: one annotated with only the characteristic parts of the instruments, and the other annotated with the entire parts of instruments. YOLOv4 and YOLOv7 were used as the image recognition system. The performance of the system was evaluated in terms of two metrics: detection accuracy (DA), which indicates the probability of correctly detecting the number of target instruments in an image, and the average precision (AP). When using YOLOv4, the mean DA and AP were 89.3% and 70.9%, respectively, when the characteristic parts of the instruments were annotated and 85.3% and 59.9%, respectively, when the entire parts of the instruments were annotated. When using YOLOv7, the mean DA and AP were 89.7% and 80.8%, respectively, when the characteristic parts of the instruments were annotated and 84.4% and 63.5%, respectively, when the entire parts of the instruments were annotated. The detection of dental instruments can be performed efficiently by targeting the parts characterizing them.

With the growth of society, people have higher and higher requirements for the quality of life, and the Internet has become an indispensable part of our daily life. Ants are very typical, common, convenient, creative and convenient. This paper mainly introduces the methods based on the Internet of Things and ant colony computing. By analyzing the research status of ant algorithm at home and abroad and relevant literature, we draw conclusions, and propose improvement plans to improve the theoretical system in this field, further optimize the image recognition application of medical equipments and medicine materials in the Internet of Things environment. Then, according to the system functions to be achieved in this paper, we determine the objective function, design indicators and parameters, so as to extract features. Finally, we get the optimal solution of the feature vector, and then send the data to the background database to obtain the recognition results, And verify the model in the experiment This paper designs a simple, low-cost, efficient and high-precision recognition system based on the ant algorithm to test. Through the image recognition experiment for medical equipments and drug materials in the Internet of Things environment, the image recognition system based on the ant algorithm achieves the feature extraction time within 20 seconds, while driving the system recognition time to reach 26 seconds, with a feature matching rate of more than 82%, which can fully meet the user’s image recognition needs, The scheme not only saves resources, but also has high practical value.