An Image Classification and Retrieval Algorithm for Product Display in E-Commerce Transactions

Content-based object organization for efficient image retrieval in image databases

The feature extraction-coding-pooling framework improves the performance of image classification because it generates robust and discriminative image representation. The proposed system uses saliency driven multi-scale nonlinear diffusion filtering with linear distance coding (LDC) method for image classification. The saliency driven multi-scale nonlinear diffusion filtering generates the images at small, mid and high scale and concatenation of information at these scales produces robust image classification using LDC. The class manifolds generated by this classification system are given as input to image retrieval system which finally retrieves all images those are relevant to supplied image.

Objectives: The objective of the examined active salient component classifier is to extract the image features from the visual substance through a novel non-parametric example based positioning methodology to utilizing comparability and learning strategies. Methods/Statistical Analysis: To establish the authenticity to avoid improper retrieval on online based image classification system called, lite Dynamic Pattern Extraction Algorithm (DPEA) for Image Classification and salient image extraction algorithm is designed. DPEA Algorithm on each benchmark dataset works on user query basis and reducing the overhead incurred during user query processing by applying labeling process. Next, by retrieving salient features on images with zero mean for each client query and each image retrieval reduces the execution time and complexity as the database does not maintain the related features. Finally, the Potential image Classification and retrieval prevents the unauthorized user modification on image data, therefore improving the reality. Here a Web Image Dataset (NUS-WIDE) created by lab of media search in National University of Singapore. The computer vision CIFAR-10 dataset, Modified National Institute of Standards and Technology database of USA (MNIST) dataset is used for experiment. A series of simulation results are performed to test the image retrieval efficiency, execution time, performance fitness for obtaining efficiency of image data handling and measure the effectiveness of DPEA Algorithm. Findings: The tests were directed on the dataset for image classification and retrieval on each region of the images. The Proposed DPEA offers better performance with an improvement of the data confidentiality by 18.72%, reduces execution complexity by 7.98%, reduces average retrieval overhead by 6.65% and also minimize retrieval complexity by 15.57% compared to existing algorithms of LFDA, PCA and PCCA respectively. Application/Improvements: It can be further extended with implementation of new retrieval techniques with different parameters which improves more retrieval efficiency and performance integrity.

In recent years, content-based image retrieval method has attracted the attention of many researchers. With the emergence of large-scale computer vision data set, large-scale image classification is going to become an important challenge in the field of computer vision. The existing image classification algorithms mainly have the following defects: (1) lack of sufficient theoretical basis; (2) lower classification accuracy and larger error; (3) algorithm running time is too long because of large amount of data. In order to solve these problems, we introduce an algorithm based on visual saliency and feature extraction theory. Visual saliency means that intelligent algorithm can mark the significant areas in the picture through the simulation of human visual characteristics, and we can preliminarily screen the large-scale date set in terms of saliency extraction, in order to constitute an initial categories set. Image classification mainly includes three processes, that are feature extraction, computation of image pattern vector, classification. Feature extraction is the key factor that affects the performance of image classification. Comparing to global features of image with blur background, partial occlusion, and illumination changes, local features are mode adaptive. Traditional image classification algorithms only use single feature, thus these methods bring limitations. In this paper, we have a thorough research of image classification methods based on feature combination, and we also propose an algorithm based on multiple feature. At the same time, in order to solve the problem that traditional methods dealing with the whole image in a non-hierarchical way, we introduce the theory of visual saliency detection. The results obviously shows that efficient feature extraction combined with the theory of visual saliency are significant to image classification.

Several Deep Learning (DL) and medical image Machine Learning (ML) methods have been investigated for efficient data representations of medical images, such as image classification, Content-Based Image Retrieval (CBIR), and image segmentation. CBIR helps medical professionals make decisions by retrieving similar cases and images from electronic medical image databases. CBIR needs expressive data representations for similar image identification and knowledge discovery in massive medical image databases explored by distinct algorithmic methods. In this study, an Improved Whale Optimization Algorithm with Deep Learning-Driven Retinal Fundus Image Grading and Retrieval (IWOADL-RFIGR) approach was developed. The presented IWOADL-RFIGR method mainly focused on retrieving and classifying retinal fundus images. The proposed IWOADL-RFIGR method used the Bilateral Filtering (BF) method to preprocess the retinal images, a lightweight Convolutional Neural Network (CNN) based on scratch learning with Euclidean distance-based similarity measurement for image retrieval, and the Least Square Support Vector Machine (LS-SVM) model for image classification. Finally, the IWOA was used as a hyperparameter optimization technique to improve overall performance. The experimental validation of the IWOADL-RFIGR model on a benchmark dataset exhibited better performance than other models.

Large-scale datasets are essential for the success of deep learning in image retrieval. However, manual assessment errors and semi-supervised annotation techniques can lead to label noise even in popular datasets. As previous works primarily studied annotation quality in image classification tasks, it is still unclear how label noise affects deep learning approaches to image retrieval. In this work, we show that image retrieval methods are less robust to label noise than image classification ones. Furthermore, we, for the first time, investigate different types of label noise specific to image retrieval tasks and study their effect on model performance.

Image retrieval systems play a crucial role in a variety of applications, from digital asset management to medical imaging and security. This paper presents a comparative analysis of current image retrieval methods, focusing on their effectiveness, efficiency, and applicability across different contexts. We systematically evaluate several prominent techniques, including content-based image retrieval (CBIR), semantic-based retrieval, and hybrid approaches that combine multiple methodologies. The evaluation criteria encompass retrieval accuracy, computational complexity, and user interaction effectiveness. Through a series of experiments and case studies, we assess the performance of these methods using benchmark datasets and real-world scenarios. Our analysis highlights the strengths and limitations of each approach, providing insights into their suitability for specific applications. The findings aim to guide practitioners and researchers in selecting the most appropriate image retrieval method based on their needs and constraints. This study contributes to the understanding of image retrieval technologies and their impact on information retrieval systems.

Content-Based Image Retrieval is an accurate characterization of visual information used for medical and natural image classification, retrieval, face recognition, etc. In recent years, deep networks achieved state-of-the-art accuracy in various vision tasks. In this paper, we propose an end-to-end approach for medical image retrieval. The proposed approach comprises a novel deep network for classification of input query image followed by the retrieval module to retrieve the images belongs to the query image class. The proposed network comprises of multi-scale filter bank for robust feature extraction. We make use of skip connections to share the initially learned features across the network. The performance of the proposed network for medical image retrieval is validated in terms of precision and recall on three publicly available medical image databases. We validated the proposed approach for two different image modalities, namely CT scans and MRI scans. Performance evaluation depicts that proposed RetrieveNet outperforms other existing methods for medical image retrieval.

Dimensionality reduction (DR) of image features plays an important role in image retrieval and classification tasks. Recently, two types of methods have been proposed to improve both the accuracy and efficiency for the dimensionality reduction problem. One uses Non-negative matrix factorization (NMF) to describe the image distribution on the space of base matrix. Another one for dimension reduction trains a subspace projection matrix to project original data space into some low-dimensional subspaces which have deep architecture, so that the low-dimensional codes would be learned. At the same time, the graph based similarity learning algorithm which tries to exploit contextual information for improving the effectiveness of image rankings is also proposed for image class and retrieval problem. In this paper, after above two methods mentioned are utilized to reduce the high-dimensional features of images respectively, we learn the graph based similarity for the image classification problem. This paper compares the proposed approach with other approaches on an image database.

The classification of logos is a particular case within computer vision since they have their own characteristics. Logos can contain only text, iconic images or a combination of both, and they usually include figurative symbols designed by experts that vary substantially besides they may share the same semantics. This work presents a method for multi-label classification and retrieval of logo images. For this, Convolutional Neural Networks (CNN) are trained to classify logos from the European Union TradeMark (EUTM) dataset according to their colors, shapes, sectors and figurative designs. An auto-encoder is also trained to learn representations of the input images. Once trained, the neural codes from the last convolutional layers in the CNN and the central layer of the auto-encoder can be used to perform similarity search through kNN, allowing us to obtain the most similar logos based on their color, shape, sector, figurative elements, overall features, or a weighted combination of them provided by the user. To the best of our knowledge, this is the first multi-label classification method for logos, and the only one that allows retrieving a ranking of images with these criteria provided by the user.

Today, image classification is considered as one of the most important and challenging tasks in computer vision. This paper presents a new method for image classification using Bag Of Visual Words and Local Binary Patterns (LBP). The bag-of-visual-words (BoVW) model has been proven to be very efficient for image classification and image retrieval. However, most proposals directly use local features extracted from an image while ignoring hidden information that could be extracted from an image. To solve this problem, we propose a novel image classification method using information extracted from different channels of the image and the grayscale version of the image. In this way more discriminant information is extracted from the image and as a result the constructed BoVW model gives highly discriminative features that considerably increases the classification performance. In this work we embed features extracted using LBP into BoVW model to construct our proposed scene classification model. The choice of LBP as image feature descriptor is because of the fact that the content of most of the scene images contains textural information so extracting LBP features is a very wise choice compared to other popular image features like Scale Invariant Feature Transform (SIFT) that fails to capture image information in homogeneous areas or textual images. Experiments on Oliva and Torralba (OT) dataset demonstrate the effectiveness of the proposed method.

Purpose – As it transforms into a consumer-led e-commerce market, we present the legal applicability of the CISG to disputes arising from international e-commerce. Design/Methodology/Approach – Disputes arising from international e-commerce are mostly about contracts, and considering the principle of internationality of a CISG sales contract and the scope of human application, it can be seen that disputes arising from consumer-led e-commerce can be subject to CISG. Findings – Through case law analysis, a new perspective on the deficiencies of the agreement that occurred in consumer-led international e-commerce was presented, along with the burden of proof, thereby increasing the applicability of CISG in B2C transactions and protecting buyers. Research Implications – Disputes arising from international e-commerce mostly concern contracts. Since e-commerce is related to the form of the contract and includes transactions concluded electronically, CISG is applied in disputes related to the contract of sale by electronic means. Among the provisions of the Convention, the scope of purchase intention should be revised to be applied more broadly by pointing out that the buyer's intention is not limited to one, and the scope of the consumer's purchase intention is narrow through the case law of Article 2a, which causes many disputes in consumer-oriented e-commerce. In addition, if a seller proves that he did not know the buyer's purchase intention, the applicability of the clause may increase, so detailed provisions on the burden of proof of purchase intention should be added.

ABSTRACTAlthough online product recommendation (OPR) is important in e-commerce transactions, there is a little understanding about differential impact of different recommendations. This study aims to examine the distinct effects of system-generated recommendation (SGR) and consumer-generated recommendation (CGR) on affective and social-psychological beliefs of OPR evaluation and to assess how they mediate the impact of OPR usage on purchase intentions. Results of a cross-sectional survey with 482 Amazon consumers showed that users of CGR express significantly higher trusting beliefs than users of SGR, while users of SGR elicit greater perceived enjoyment than users of CGR, resulting in mediating effect on purchase intentions. Moreover, CGRs were found to elicit greater trusting beliefs for experience products, while SGRs were found to unfold greater perceived enjoyment for search products.

This work presents a new approach for classification and retrieval of echocardiographic images from textual information of the anatomical structures and diagnosis features. These textual attributes will be acquired from the electronic medical report generated in an integrated healthcare environment. The medical report is provided by a specialist in the area during the analysis of the medical image stored in a PACS environment. Such innovation guarantees a more accurate classifier and a better optimization of the medical work, since the medical report and the attributes for the medical image classifier will be created at the same time. The system is being developed in the University Hospital of the University of Brasilia.

Although the existing traditional image classification methods have been widely applied in practical problems, there are some problems in the application process, such as unsatisfactory effects, low classification accuracy, and weak adaptive ability. This method separates image feature extraction and classification into two steps for classification operation. The deep learning model has a powerful learning ability, which integrates the feature extraction and classification process into a whole to complete the image classification test, which can effectively improve the image classification accuracy. However, this method has the following problems in the application process: first, it is impossible to effectively approximate the complex functions in the deep learning model. Second, the deep learning model comes with a low classifier with low accuracy. So, this paper introduces the idea of sparse representation into the architecture of the deep learning network and comprehensively utilizes the sparse representation of well multidimensional data linear decomposition ability and the deep structural advantages of multilayer nonlinear mapping to complete the complex function approximation in the deep learning model. And a sparse representation classification method based on the optimized kernel function is proposed to replace the classifier in the deep learning model, thereby improving the image classification effect. Therefore, this paper proposes an image classification algorithm based on the stacked sparse coding depth learning model-optimized kernel function nonnegative sparse representation. The experimental results show that the proposed method not only has a higher average accuracy than other mainstream methods but also can be good adapted to various image databases. Compared with other deep learning methods, it can better solve the problems of complex function approximation and poor classifier effect, thus further improving image classification accuracy.