Content-based Image Classification Research Articles

ATiTHi: A Deep Learning Approach for Tourist Destination Classification using Hybrid Parametric Optimization

A picture is best way to explore the tourist destination by visual content. The content-based image classification of tourist destinations makes it possible to understand the tourism liking by providing a more satisfactory tour. It also provides an important reference for tourist destination marketing. To enhance the competitiveness of the tourism market in India, this research proposes an innovative tourist spot identification mechanism by identifying the content of significant numbers of tourist photos using convolutional neural network (CNN) approach. It overcomes the limitations of manual approaches by recognizing visual information in photos. In this study, six thousand photos from different tourist destinations of India were identified and categorized into six major categories to form a new dataset of Indian Trajectory. This research employed Transfer learning (TF) strategies which help to obtain a good performance measure with very small dataset for image classification.VGG-16, VGG-19, MobileNetV2, InceptionV3, ResNet-50 and AlexNet CNN model with pretrained weight from ImageNet dataset was used for initialization and then an adapted classifier was used to classify tourist destination images from the newly prepared dataset. Hybrid hyperparameter optimization employ to find out hyperparameter for proposed Atithi model which lead to more efficient model in classification. To analyse and compare the performance of the models, known performance indicators were selected. As compared to the AlexNet model (0.83), MobileNetV2(0.93), VGG-19(0.918), InceptionV3(0.89), ResNet-50(0.852) the VGG16 model has performed the best in terms of accuracy (0.95). These results show the effectiveness of the current model in tourist destination image classification.

Fusion of vectored text descriptors with auto extracted deep CNN features for improved image classification

• Transfer learning approach on pre-trained DCNN models for the WANG dataset. • Using word2cev for creating an embedding vector followed by a combination of DSSM and LSTM to reduce the size of a word vector and using these new word vectors to assign five synonyms for each label or keyword for an image to improve classification accuracy. • Fusion of auto extracted features from pre-trained models and word to vector features obtained from word2vec, DSSM, and LSTM for improved content-based image classification (CBIC). In today's age, massive image data is generated rapidly. This influx has made labeling images tedious and, in turn, made it harder to retrieve images through searching algorithms that rely only on labels, keywords, or other meta-data in the images. Modern Content-Based Image Retrieval (CBIR) techniques rely on the visual features within the image to return relevant results to a search query. Deep Convolutional Neural Network (DCNN) models made great strides in the last decade. This paper relies on these complex pre-trained models to extract visual features from images. The proposed work has used pre-trained models like VGG16, MobileNet, Inceptionv3, and Xception for this task. Some studies in the CBIR space also suggest increased accuracy when both visual and textual features are considered. This paper proposes a novel three-step process for obtaining textual features. Firstly, the proposed model receives keywords for each image using Google Cloud Vision API. Secondly, the proposed model replaces each keyword with a 300-dimensional embedding vector obtained using word2vec, trained on the Google News dataset. Finally, the proposed model trains a combination of the Deep Semantic Similarity Model (DSSM) and Long Short-Term Memory (LSTM) model to reduce the 300-dimensional vector to a 64-dimensional vector. Using these new shortened word vectors, the proposed model computes the cosine similarity to replace each keyword of an image with five of its synonyms. Here, these additional steps increased the accuracy compared to simply using a word embedding technique. Finally, the proposed model combined the visual and textual feature vectors and observed that this feature set showed maximum classification accuracy of 98.33%, which is also compared with and found relatively better than other similar model results.

COMPARISON STUDY BETWEEN IMAGE RETRIEVAL METHODS

Searching for a relevant image in an archive is a problematic research issue for the computer vision research community. The majority of search engines retrieve images using traditional text-based approaches that rely on captions and metadata. Extensive research has been reported in the last two decades for content-based image retrieval (CBIR), analysis, and image classification. Content-Based Image Retrieval is a process that provides a framework for image search, and low-level visual features are commonly used to retrieve the images from the image database. The essential requirement in any image retrieval process is to sort the images with a close similarity in terms of visual appearance. The shape, color, and texture are examples of low-level image features. In image classification-based models and CBIR, high-level image visuals are expressed in the form of feature vectors made up of numerical values. The researcher's findings a significant gap between human visual comprehension and image feature representation. In this paper, we plan to present a comparison study and a comprehensive overview of the recent developments in the field of CBIR and image representation.

Hybrid descriptor definition for content based image classification using fusion of handcrafted features to convolutional neural network features

Hybrid descriptor definition for content based image classification using fusion of handcrafted features to convolutional neural network features

An industrial-grade solution for agricultural image classification tasks

With artificial intelligence to promote the rapid development of precision agriculture, the management and detection of agricultural resources through computer vision and deep learning is particularly important. Content-Based image classification has produced extensive research, however relative research is still only at the theoretical level. We therefore put forward a high-performance, low-cost, powerful applicability and very feasible scheme to solve many problems which image classification is facing today in agricultural automation. Firstly, we use a fine-tuning strategy to train models to better performance in classification tasks. Secondly, we utilize neural network pruning techniques to reduce neural network size and computational cost, and subsequently retrain models by knowledge distillation to minimize pruned model performance loss. Thirdly, converting trained models to an available ONNX format, thus simplifying the process from theory to practice. And finally, we deploy and inference models in a high-performance deep learning inference platform with C++, that is, NCNN. We conducted experiments on three representative agricultural image classification datasets, PlantVillage, DeepWeeds and Flowers102. The results demonstrate the effectiveness of our scheme.

A Novel Feature Extraction Technique for Content Based Image Classification in Digital Marketing Platform

Increasing size and complexity of information about different products offered through digital media has made it essential to target the effective and efficient techniques of data management and categorization. Text data has gradually been replaced by image or visual data due to increasing importance of image capturing devices and social media. Images have been used as one of the foremost linkages between the brand and the consumer in digital marketing domain. Classification has been considered as a vital component of machine learning necessary for data identification which can be initiated before retrieval to restrict the search within the class of interest. The authors have proposed a novel technique for feature extraction for content based image classification. Analyses of customer satisfaction related to content based product identification with images in diverse media have also been carried out. The classification results with the proposed technique have outperformed the existing methods and have shown an increment of 20% in precision results.

Adaptive Multimodal Feature Fusion for Content-Based Image Classification and Retrieval

Adaptive Multimodal Feature Fusion for Content-Based Image Classification and Retrieval

Large-Scale Multi-modal Distance Metric Learning with Application to Content-Based Information Retrieval and Image Classification

Metric learning algorithms aim to make the conceptually related data items closer and keep dissimilar ones at a distance. The most common approach for metric learning on the Mahalanobis method. Despite its success, this method is limited to find a linear projection and also suffer from scalability respecting both the dimensionality and the size of input data. To address these problems, this paper presents a new scalable metric learning algorithm for multi-modal data. Our method learns an optimal metric for any feature set of the multi-modal data in an online fashion. We also combine the learned metrics with a novel Passive/Aggressive (PA)-based algorithm which results in a higher convergence rate compared to the state-of-the-art methods. To address scalability with respect to dimensionality, Dual Random Projection (DRP) is adopted in this paper. The present method is evaluated on some challenging machine vision datasets for image classification and Content-Based Information Retrieval (CBIR) tasks. The experimental results confirm that the proposed method significantly surpasses other state-of-the-art metric learning methods in most of these datasets in terms of both accuracy and efficiency.

Assorted Techniques for Defining Image Descriptors to Augment Content Based Classification Accuracy

Image data has turned out to be a significant means of expression with the advancements of digital image processing technologies. Image capturing devices has now transformed to commodities due to smart integration with cell phones and other useful devices. Huge amount of images are getting accumulated daily in gigantic databases which requires categorization for prompt retrieval in real time. Content based image classification (CBIC) thus gained it's popularity in classifying images to their corresponding categories. Feature extraction techniques are the foundation of CBIC to represent the image data in the form of feature vectors. This work has implemented three different feature extraction techniques from spatial domain, transform domain and deep learning domain. The three different feature vectors feature vector are contrasted to investigate the robustness of descriptor definition for content based image classification

Content-Based E-Commerce Image Classification Research

The 21st century is the era of big data in the Internet. Online shopping has become a trend, and e-commerce has developed rapidly. With the exponential increase of the amount of commodity image data, the management of massive commodity image database restricts the development of e-commerce to some extent. In order to effectively manage goods and improve the accuracy and efficiency of product image retrieval, this paper uses content-based methods to classify e-commerce images. Aiming at the problems of insufficient classification accuracy and long classification training time in e-commerce image classification, an adaptive momentum learning rate based LBP-DBN training algorithm-AML-LBP-DBN and commodity image classification method based on image local feature multi-level clustering and image-class nearest neighbor classifier are proposed. By simulating the commodity identification dataset RPC, the results show that the proposed method has obvious advantages in the classification training time and classification accuracy of e-commerce images.

A Novel Feature Extraction Technique for Content Based Image Classification in Digital Marketing Platform

A Novel Feature Extraction Technique for Content Based Image Classification in Digital Marketing Platform

Computer Vision Systems for Content-based Image Classification

In this paper, computer vision based Content-Based Image Classification systems have been described which are useful in various service and product industries. We have proposed Confidence Co-occurrence Matrix, which is a modification of Generalized Co-occurrence Matrix. The proposed framework merges properties of Confidence Co-occurrence Matrix along with other features such as RGB and HSV Histograms, Local Binary Pattern and Canny’s edge detection approach. Proposed approach creates a fixed- size descriptor of size 1632. Once a feature vector has been constructed, classification is performed using Linear Support Vector Machine. The System is tested on four different wellknown datasets namely, sport events Database, Flavia Leaf Dataset, Leeds Butterfly Dataset and Birds Dataset . The proposed system is implemented in MATLAB and achieves an average class accuracy of 96%, 99%,95% and 95% for the four datasets respectively

Melanoma Identification with Content based Image Classification using Bit Plane Features

Augmented episodes of melanoma, a curable skin cancer variety of antagonistic nature, have stimulated the advancements in designing systems for computer aided diagnosis of the disease. Clinical diagnosis includes primary vetting of the symptoms followed by a biopsy and necessary medical examinations. However, computer based classification of the clinical images of dermoscopy have the potential to diminish the exertion of the dermatologist by offering a computer aided opinion independent of medical know-how. Assorted methods are proposed in recent times including the deep learning techniques for computer based melanoma recognition. But, most of the techniques have enhanced computational overhead which has added to the computational complexity of the entire system. In this work, the authors have attempted to design light-weight feature extraction techniques from high level bit planes of dermoscopic images by ignoring the noisy slices of bit planes for robust feature extraction. The proposed method of feature extraction is tested with three different classifiers for specificity and sensitivity outputs of the dermoscopic images. The results of classification have outclassed the performance of state-of-the-art feature extraction techniques.

Improved object recognition results using SIFT and ORB feature detector

Object recognition has a wide domain of applications such as content-based image classification, video data mining, video surveillance and more. Object recognition accuracy has been a significant concern. Although deep learning had automated the feature extraction but hand crafted features continue to deliver consistent performance. This paper aims at efficient object recognition using hand crafted features based on Oriented Fast & Rotated BRIEF (Binary Robust Independent Elementary Features) and Scale Invariant Feature Transform features. Scale Invariant Feature Transform (SIFT) are particularly useful for analysis of images in light of different orientation and scale. Locality Preserving Projection (LPP) dimensionality reduction algorithm is explored to reduce the dimensions of obtained image feature vector. The execution of the proposed work is tested by using k-NN, decision tree and random forest classifiers. A dataset of 8000 samples of 100-class objects has been considered for experimental work. A precision rate of 69.8% and 76.9% has been achieved using ORB and SIFT feature descriptors, respectively. A combination of ORB and SIFT feature descriptors is also considered for experimental work. The integrated technique achieved an improved precision rate of 85.6% for the same.

Content-Based Image Retrieval and Feature Extraction: A Comprehensive Review

Multimedia content analysis is applied in different real-world computer vision applications, and digital images constitute a major part of multimedia data. In last few years, the complexity of multimedia contents, especially the images, has grown exponentially, and on daily basis, more than millions of images are uploaded at different archives such as Twitter, Facebook, and Instagram. To search for a relevant image from an archive is a challenging research problem for computer vision research community. Most of the search engines retrieve images on the basis of traditional text-based approaches that rely on captions and metadata. In the last two decades, extensive research is reported for content-based image retrieval (CBIR), image classification, and analysis. In CBIR and image classification-based models, high-level image visuals are represented in the form of feature vectors that consists of numerical values. The research shows that there is a significant gap between image feature representation and human visual understanding. Due to this reason, the research presented in this area is focused to reduce the semantic gap between the image feature representation and human visual understanding. In this paper, we aim to present a comprehensive review of the recent development in the area of CBIR and image representation. We analyzed the main aspects of various image retrieval and image representation models from low-level feature extraction to recent semantic deep-learning approaches. The important concepts and major research studies based on CBIR and image representation are discussed in detail, and future research directions are concluded to inspire further research in this area.

Parameter optimization of a multiscale descriptor for shape analysis on healthcare image datasets

Shape analysis is a key task in computer vision, and multiscale descriptors can significantly enhance shape characterization. However, these descriptors often rely on parameter adjustments to configure a meaningful set of scales that can enable shape analysis. Parameter adjustment in large image datasets is often done on a trial-and-error basis, and an alternative solution to mitigate such a limitation is the use of metaheuristic optimization. The main contribution of this paper is to provide a strategy that supports the automatic parameter adjustment of a multiscale descriptor within a metaheuristic optimization algorithm, where the choice of the cost function strongly influences and boosts the performance of the shape description, which is closely related to the problem domain, i.e. the image dataset. Our research considers synthetic data in a prior evaluation of the cost functions that optimize the scale parameters of the Normalized Multiscale Bending Energy (NMBE) descriptor through the Simulated Annealing (SA) metaheuristic. The cost functions that drive this metaheuristic are: Silhouette (SI), the Davies–Bouldin index (DB) and the Calinski-Harabasz index (CH). We conduct content-based image retrieval and classification experiments to assess the optimized descriptor using three healthcare image datasets: Amphetamine Type Stimulants (ATS) pills (Illicit Pills), pills from the National Library of Medicine (NLM Pills) and hand alphabet gestures (Hands). We also provide segmentation masks for Illicit Pills to guarantee reproducibility. We report the results of tests using a state-of-art method based on a deep neural network, Inception-ResNet-v2. The optimized NMBE with SI and DB achieved competitive and accurate values of above 94%, in terms of both the Mean Average Precision measure (MAP) and Accuracy (ACC) for Illicit Pills and NLM Pills. The precision recall curves demonstrate that it outperforms the Inception-ResNet-v2 for both of these datasets.

Content-based high-resolution satellite image classification

Content-based image classification has produced successful and automated applications in various service and product industries. In this paper, high-resolution satellite scene classification based on multiple feature combination is considered. We have proposed confidence co-occurrence matrix, which is a modification of the generalized co-occurrence matrix. The proposed framework combines RGB histogram, HSV histogram, local binary pattern, confidence co-occurrence matrix properties and Canny’s edge detection approach. The approach creates a fixed-size feature vector of size 1632. Once a feature vector has been constructed, classification is performed using linear support vector machine. The system is tested using widely popular benchmark Satellite Scene dataset and UC Merced land used dataset having 19 and 21 classes respectively. The proposed system also works well in agricultural science. The system is also tested on folio dataset having 32 species of leaf. The proposed system is implemented in MATLAB and achieves an average class classification accuracy of 99%.

The Application of Content-based Image Emotional Semantic Recognition and Classification in Clothing E-commerce

People dress more and more sensual, more and more people like to wear clothing in line with their emotional expression, and online shopping convenience makes a lot of people like to buy clothing online, and the current clothing ecommerce websites do not classify clothing with their emotional semantic which could bring a certain inconvenience to the online buyers. Content-based image recognition and retrieval technology takes technical support for the emotional semantic automatic identification and classification of clothing commodity in the clothing e-commerce site. All the issues had been studied in this article which took clothing fabrics as an example to illustrate. All the work wants to cause the industry's attention.

Content Based Image Classification Using Support Vector Machine Algorithm

Content Based Image Classification Using Support Vector Machine Algorithm

Decision fusion-based approach for content-based image classification

PurposeCurrent practices in data classification and retrieval have experienced a surge in the use of multimedia content. Identification of desired information from the huge image databases has been facing increased complexities for designing an efficient feature extraction process. Conventional approaches of image classification with text-based image annotation have faced assorted limitations due to erroneous interpretation of vocabulary and huge time consumption involved due to manual annotation. Content-based image recognition has emerged as an alternative to combat the aforesaid limitations. However, exploring rich feature content in an image with a single technique has lesser probability of extract meaningful signatures compared to multi-technique feature extraction. Therefore, the purpose of this paper is to explore the possibilities of enhanced content-based image recognition by fusion of classification decision obtained using diverse feature extraction techniques.Design/methodology/approachThree novel techniques of feature extraction have been introduced in this paper and have been tested with four different classifiers individually. The four classifiers used for performance testing were K nearest neighbor (KNN) classifier, RIDOR classifier, artificial neural network classifier and support vector machine classifier. Thereafter, classification decisions obtained using KNN classifier for different feature extraction techniques have been integrated by Z-score normalization and feature scaling to create fusion-based framework of image recognition. It has been followed by the introduction of a fusion-based retrieval model to validate the retrieval performance with classified query. Earlier works on content-based image identification have adopted fusion-based approach. However, to the best of the authors’ knowledge, fusion-based query classification has been addressed for the first time as a precursor of retrieval in this work.FindingsThe proposed fusion techniques have successfully outclassed the state-of-the-art techniques in classification and retrieval performances. Four public data sets, namely, Wang data set, Oliva and Torralba (OT-scene) data set, Corel data set and Caltech data set comprising of 22,615 images on the whole are used for the evaluation purpose.Originality/valueTo the best of the authors’ knowledge, fusion-based query classification has been addressed for the first time as a precursor of retrieval in this work. The novel idea of exploring rich image features by fusion of multiple feature extraction techniques has also encouraged further research on dimensionality reduction of feature vectors for enhanced classification results.