Image Classification Algorithm Research Articles

Efficient adaptive learning rate for convolutional neural network based on quadratic interpolation egret swarm optimization algorithm

Convolutional neural network (CNN) has recently become popular for addressing multi-domain image classification. However, most existing methods frequently suffer from poor performance, especially in performance and convergence for various datasets. Herein, we have proposed an algorithm for multi-domain image classification by introducing a novel adaptive learning rate rule to the conventional CNN. Specifically, we adopt the CNN to extract rich feature representations. Given that the hyperparameters of the learning rate have a positive effect on the prediction error, the Egret Swarm Optimization Algorithm (ESOA) is introduced to update the learning rate, which can jump out of local extrema during exploration. Therefore, combined with quadratic interpolation, the objective function can be approximated by a polynomial, thereby improving its prediction accuracy. To verify the robustness of the proposed algorithm, we conducted comprehensive experiments in five domain public datasets to fulfil the task of image classification. Meanwhile, the highest accuracy rate of 97.15 % was obtained on the test set. The performances of our method on 24 benchmark functions (CEC2017 and CEC2022) are compared with Particle Swarm Optimization (PSO), Genetic Algorithm(GA), Whale Optimization Algorithm(WOA), Catch Fish Optimization Algorithm(CFOA), GOOSE Algorithm(GO) and ESOA. In two benchmark sets, the performance metric values of our algorithm rank no. 1, especially in all unimodal functions in contrast with other baseline algorithms.

Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output

Text Message System for the Prediction of Colonoscopy Bowel Preparation Adequacy Before Colonoscopy: An Artificial Intelligence Image Classification Algorithm Based on Images of Stool Output

Gated Graph Attention-based Crossover Snake (GGA-CS) Algorithm for Hyperspectral Image Classification

Gated Graph Attention-based Crossover Snake (GGA-CS) Algorithm for Hyperspectral Image Classification

The SLICE-3D dataset: 400,000 skin lesion image crops extracted from 3D TBP for skin cancer detection

AI image classification algorithms have shown promising results when applied to skin cancer detection. Most public skin cancer image datasets are comprised of dermoscopic photos and are limited by selection bias, lack of standardization, and lend themselves to development of algorithms that can only be used by skilled clinicians. The SLICE-3D (“Skin Lesion Image Crops Extracted from 3D TBP”) dataset described here addresses those concerns and contains images of over 400,000 distinct skin lesions from seven dermatologic centers from around the world. De-identified images were systematically extracted from sensitive 3D Total Body Photographs and are comparable in optical resolution to smartphone images. Algorithms trained on lower quality images could improve clinical workflows and detect skin cancers earlier if deployed in primary care or non-clinical settings, where photos are captured by non-expert physicians or patients. Such a tool could prompt individuals to visit a specialized dermatologist. This dataset circumvents many inherent limitations of prior datasets and may be used to build upon previous applications of skin imaging for cancer detection.

An Improved Medical Image Classification Algorithm Based on Adam Optimizer

Due to the complexity and illegibility of medical images, it brings inconvenience and difficulty to the diagnosis of medical personnel. To address these issues, an optimization algorithm called GSL(Gradient sine linear) based on Adam algorithm improvement is proposed in this paper, which introduces gradient pruning strategy, periodic adjustment of learning rate, and linear interpolation strategy. The gradient trimming technique can scale the gradient to prevent gradient explosion, while the periodic adjustment of the learning rate and linear interpolation strategy adjusts the learning rate according to the characteristics of the sinusoidal function, accelerating the convergence while reducing the drastic parameter fluctuations, improving the efficiency and stability of training. The experimental results show that compared to the classic Adam algorithm, this algorithm can demonstrate better classification accuracy, the GSL algorithm achieves an accuracy of 78% and 75.2% on the MobileNetV2 network and ShuffleNetV2 network under the Gastroenterology dataset; and on the MobileNetV2 network and ShuffleNetV2 network under the Glaucoma dataset, an accuracy of 84.72% and 83.12%. The GSL optimizer achieved significant performance improvement on various neural network structures and datasets, proving its effectiveness and practicality in the field of deep learning, and also providing new ideas and methods for solving the difficulties in medical image recognition.

MCNN+: Gemstone Image Classification Algorithm with Deep Multi-feature Fusion CNNs

MCNN+: Gemstone Image Classification Algorithm with Deep Multi-feature Fusion CNNs

A review of federated learning algorithms in image classification

Image classification is one of the most popular applications of machine learning. It has shown its potential in fields like healthcare, auto-driving and face recognition. Federated learning (FL) emerged in 2017, creating a major innovation to the field. The new structure brings new possibilities, but create new challenges such as data heterogeneity, privacy leakage and communication burdens in parameter updating. The paper solves the problem that there are relatively few papers providing a complete analysis relating to the application of FL in image classification. The paper contributes to describe the new challenges of FL in image classification and show the related reasons behind respectively, then analyze the current state-of-the-art algorithms designed for solving the challenges and improving image model performance by discussing the basic ideas and steps of algorithms and showing their pros and cons. The paper further more contributes to compare the performance of each model in accuracy and communication speed, and outline several possible directions for future advancement.

Multi-objective evolutionary multi-tasking band selection algorithm for hyperspectral image classification

Hyperspectral images (HSI) contain a great number of bands, which enable better characterization of features. However, the huge dimension and information volume brought by the abundant bands may give rise to a negative influence on the efficiency of subsequent processing on hyperspectral images. Band selection (BS) is a commonly adopted to reduce the dimension of HSIs. Different from the previous work, in this paper, hyperspectral band selection problem is formulated as a multi-objective optimization problem, where the band distribution uniformity among the selected bands and inter-class separation distance from a few labeled samples are optimized simultaneously. To fully exploit the relation between the band subsets with different sizes, we construct a multi-objective evolutionary multi-tasking algorithm for hyperspectral band selection (namely MEMT-HBS) to achieve the selected band subsets for all the selected band sizes in one run. To implement MEMT-HBS, the intra-task pairwise learning based solution generation strategy is suggested to evolve the population for each task to achieve high-quality offspring whose selected band size is restricted to a fixed scope. The inter-task band coverage based knowledge transferring strategy is utilized to choose useful individuals from adjacent tasks to further enhance the performance of current task. Compared with the state-of-the-art semi-supervised and unsupervised BS algorithms, empirical results on different standard hyperspectral datasets show that our proposed MEMT-HBS can determine the superior band subset which has a higher image classification accuracy over the comparison algorithms.

Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI Pooling.

Weakly supervised object detection (WSup-OD) increases the usefulness and interpretability of image classification algorithms without requiring additional supervision. The successes of multiple instance learning in this task for natural images, however, do not translate well to medical images due to the very different characteristics of their objects (i.e. pathologies). In this work, we propose Weakly Supervised ROI Proposal Networks (WSRPN), a new method for generating bounding box proposals on the fly using a specialized region of interest-attention (ROI-attention) module. WSRPN integrates well with classic backbone-head classification algorithms and is end-to-end trainable with only image-label supervision. We experimentally demonstrate that our new method outperforms existing methods in the challenging task of disease localization in chest X-ray images. Code: https://anonymous.4open.science/r/WSRPN-DCA1.

An Interpretable Breast Ultrasound Image Classification Algorithm Based on Convolutional Neural Network and Transformer

An Interpretable Breast Ultrasound Image Classification Algorithm Based on Convolutional Neural Network and Transformer

Breast Cancer Detection and Analytics Using Hybrid CNN and Extreme Learning Machine.

Early detection of breast cancer is essential for increasing survival rates, as it is one of the primary causes of death for women globally. Mammograms are extensively used by physicians for diagnosis, but selecting appropriate algorithms for image enhancement, segmentation, feature extraction, and classification remains a significant research challenge. This paper presents a computer-aided diagnosis (CAD)-based hybrid model combining convolutional neural networks (CNN) with a pruned ensembled extreme learning machine (HCPELM) to enhance breast cancer detection, segmentation, feature extraction, and classification. The model employs the rectified linear unit (ReLU) activation function to enhance data analytics after removing artifacts and pectoral muscles, and the HCPELM hybridized with the CNN model improves feature extraction. The hybrid elements are convolutional and fully connected layers. Convolutional layers extract spatial features like edges, textures, and more complex features in deeper layers. The fully connected layers take these features and combine them in a non-linear manner to perform the final classification. ELM performs classification and recognition tasks, aiming for state-of-the-art performance. This hybrid classifier is used for transfer learning by freezing certain layers and modifying the architecture to reduce parameters, easing cancer detection. The HCPELM classifier was trained using the MIAS database and evaluated against benchmark methods. It achieved a breast image recognition accuracy of 86%, outperforming benchmark deep learning models. HCPELM is demonstrating superior performance in early detection and diagnosis, thus aiding healthcare practitioners in breast cancer diagnosis.

Using Machine Learning for Endoscopic Detection of Low-Grade Subglottic Stenosis: A Proof of Principle.

The current study trains, tests, and evaluates a deep learning algorithm to detect subglottic stenosis (SGS) on endoscopy. A retrospective review of patients undergoing microlaryngoscopy-bronchoscopy was performed. A pretrained image classifier (Resnet50) was retrained and tested on 159 images of airways taken at the glottis, 106 normal-sized airways, and 122 with SGS. Data augmentation was performed given the small sample size to prevent overfitting. Overall model accuracy was 73.3% (SD: 3.8). Precision and recall for stenosis were 77.3% (SD: 4.0) and 72.7 (SD: 4.0). F1 score for the detection of stenosis was 0.75 (SD: 0.04). Precision and recall for normal-sized images were lower at 69% (SD: 4.35) and 74% (SD: 4), with an F1 score of 0.71 (SD: 0.04). This study demonstrates that an image classification algorithm can identify SGS on endoscopic images. Work is needed to improve diagnostic accuracy for eventual deployment of the algorithm into clinical care.

Optimizing Convolutional Neural Networks for Image Classification on Resource-Constrained Microcontroller Units

Running machine learning algorithms for image classification locally on small, cheap, and low-power microcontroller units (MCUs) has advantages in terms of bandwidth, inference time, energy, reliability, and privacy for different applications. Therefore, TinyML focuses on deploying neural networks on MCUs with random access memory sizes between 2 KB and 512 KB and read-only memory storage capacities between 32 KB and 2 MB. Models designed for high-end devices are usually ported to MCUs using model scaling factors provided by the model architecture’s designers. However, our analysis shows that this naive approach of substantially scaling down convolutional neural networks (CNNs) for image classification using such default scaling factors results in suboptimal performance. Consequently, in this paper we present a systematic strategy for efficiently scaling down CNN model architectures to run on MCUs. Moreover, we present our CNN Analyzer, a dashboard-based tool for determining optimal CNN model architecture scaling factors for the downscaling strategy by gaining layer-wise insights into the model architecture scaling factors that drive model size, peak memory, and inference time. Using our strategy, we were able to introduce additional new model architecture scaling factors for MobileNet v1, MobileNet v2, MobileNet v3, and ShuffleNet v2 and to optimize these model architectures. Our best model variation outperforms the MobileNet v1 version provided in the MLPerf Tiny Benchmark on the Visual Wake Words image classification task, reducing the model size by 20.5% while increasing the accuracy by 4.0%.

Fine-Grained Few-Shot Image Classification Based on Feature Dual Reconstruction

Fine-grained few-shot image classification is a popular research area in deep learning. The main goal is to identify subcategories within a broader category using a limited number of samples. The challenge stems from the high intra-class variability and low inter-class variability of fine-grained images, which often hamper classification performance. To overcome this, we propose a fine-grained few-shot image classification algorithm based on bidirectional feature reconstruction. This algorithm introduces a Mixed Residual Attention Block (MRA Block), combining channel attention and window-based self-attention to capture local details in images. Additionally, the Dual Reconstruction Feature Fusion (DRFF) module is designed to enhance the model’s adaptability to both inter-class and intra-class variations by integrating features of different scales across layers. Cosine similarity networks are employed for similarity measurement, enabling precise predictions. The experiments demonstrate that the proposed method achieves classification accuracies of 96.99%, 98.53%, and 89.78% on the CUB-200-2011, Stanford Cars, and Stanford Dogs datasets, respectively, confirming the method’s efficacy in fine-grained classification tasks.

Underwater Dam Crack Image Classification Algorithm Based on Improved VanillaNet

Underwater Dam Crack Image Classification Algorithm Based on Improved VanillaNet

Overview of deep learning algorithms for PolSAR image classification

Overview of deep learning algorithms for PolSAR image classification

Rubber Leaf Image Classification Using Artificial Intelligence Methods as an Effort to Improve Plantation Production Results

Purpose: Rubber is one of the plantation commodities that contributes positively to the trade surplus in the agricultural sector. Seeing the positive trend in global rubber consumption and production, demand is expected to continue increasing in the future. To enhance rubber productivity, rubber processing technology can be used to make it more efficient, thus increasing the amount of latex extracted from the sap and reducing waste materialDesign/methodology/approach: One technology that can be developed to increase the productivity efficiency of rubber plants is by using Artificial Intelligence. This technology is expected to be implemented in the rubber plantation sector, specifically in the automatic recognition of rubber leaves.Findings/result: The measurement and performance analysis of the rubber leaf image classification algorithm based on Artificial Intelligence has also been evaluated, showing near-perfect accuracy on training data (99.86%) and very good performance on validation data (97.43%), with a very low validation loss (0.0873), indicating that the model has learned well by the last epochOriginality/value/state of the art: The population in this study consists of image data from various tree leaves, including 10 types of rubber leaves and non-rubber leaves

Multimodal breast cancer risk classifier based on biomaterial impedance analysis

Purpose of the research. Breast cancer is the most common malignant tumor among women in Europe and its early detection plays a leading role in reducing mortality rates. Currently, X-ray mammography is the standard screening method for detecting breast cancer. However, due to the morphological similarities between benign and malignant lesions, many of the positive screening mammograms are false positive (up to 40%). Therefore, automation and intellectualization of this process is an urgent task.Methods. The presented studies examine the problems of finding new, highly sensitive, prompt and non-invasive methods for detecting malignant tumors, based on the use of modern computer and telecommunication technologies, which make it possible not only to identify early manifestations of a pathological focus, but also to monitor the process of the effectiveness of therapy without significant harm to the patient’s health.Results. The presented model of a multi-channel classifier integrates the capabilities of multi-frequency bioimpedance measurements and matrix acquisition of information from the surface of human skin through multi-electrode matrix systems. To do this, based on a matrix of electrodes, 3D mapping of the skin surface in problem areas is carried out. Through multi-frequency scanning, we obtain a three-dimensional bioimpedance image, which is analyzed by a convolutional neural network and/or by a decision maker. The proposed solution allows simultaneous analysis of data by an expert (bioimpedance image) and a convolutional neural network (trained classifier), which leads to a reduction in false positive results.Conclusion. The possibilities of multichannel monitoring open up prospects for constructing impedance multidimensional "portraits" of malignant tumors. To classify “portraits” (diagnostics and preclinical diagnostics), methods and algorithms for image recognition and classification are used.

Impacts of Integrated Watershed Management Interventions on Land Use/Land Cover of Yesir Watershed in Northwestern Ethiopia

Since 2002, numerous sustainable land management (SLM) interventions have been implemented in Ethiopia, such as agroforestry, area closure, forage development, gully rehabilitation, and conservation agriculture. In addition, watershed-based developments contributed comprehensively to a better use of existing natural resources. This study determined the impact of Integrated Watershed Management (IWM) on land use/land cover for the Yesir watershed in Northern Ethiopia. Supervised image classification algorithms were applied to a time series of Landsat 5 (2002) and Landsat 8 (2013 and 2022) images to produce land use/land cover maps. A Geographic Information System was applied to analyze and map changes in land use/land cover for settlements, agricultural land, grazing land, and land covered with other vegetation. In focus group discussions, the time series maps were analyzed and compared with the integrated watershed management practices to analyze their impacts. The results document that integrated watershed management practices have contributed to a significant change in land use/land cover in the study area over the past 20 years. The quantitative analysis of land use/land cover between the years 2002 and 2022 only revealed a downward trend in agricultural land. Considering the value of the Normalized Difference Vegetation Index (NDVI) as a biophysical feature for the increase of green mass, this indicator also documents an improvement in land use/land cover with regard to sustainable land management and consequently poverty alleviation.

Adaptive Detection and Classification of Brain Tumour Images Based on Photoacoustic Imaging

A new imaging technique called photoacoustic imaging (PAI) combines the advantages of ultrasound imaging and optical absorption to provide structural and functional details of tissues. It has broad application prospects in the accurate diagnosis and treatment monitoring of brain tumours. However, the existing photoacoustic image classification algorithms cannot effectively distinguish benign tumours from malignant tumours. To address this problem, the YoLov8-MedSAM model is proposed in this research to provide precise and adaptable brain tumour identification and detection segmentation. Additionally, it employs convolutional neural networks (CNNs) to classify and identify tumours in order to distinguish between benign and malignant variations in PAI. The experimental results show that the method proposed in this study not only effectively detects and segments brain tumours of various shapes and sizes but also increases the accuracy of brain tumour classification to 97.02%. The method provides richer and more valuable diagnostic information to the clinic and effectively optimizes the diagnosis and treatment strategy of brain tumours.