[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2322":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":18,"tags":20,"view_count":15,"doi":24,"paper":25,"created_at":38},2322,"A Hybrid Deep Learning Architecture for Image Classification Across Diverse Visual Recognition Applications","https:\u002F\u002Fdoi.org\u002F10.48175\u002Fijarsct-38253","The core computer vision problem of picture categorization has several domain-specific applications. This paper's goal is to talk about the significance of picture categorization in modern technology and society, as well as its ideas, techniques, and applications. Many computer vision systems rely on image classification, where images are automatically assigned to a predetermined category, based on the information they provide in the image. This study trains a hybrid deep learning system to efficiently recognize photos using the Caltech-256 dataset. The system makes use of both Bidirectional Long Short-Term Memory (BiLSTM) and Gated Recurrent Units (GRU). Dataset preprocessing includes standardization, label encoding, damaged image identification, and duplicate reduction. After separating the dataset into a train and test set, the following step is to extract features from each. The proposed GRU+BiLSTM model is evaluated in comparison to AlexNet, MobileNetV2, EfficientNet, and CNN models using ACC, PRE, REC, and F1-score (F1). Results for ACC (98.9%), PRE (99.1%), REC (99.3%), and F1 (100%) were better using the suggested method compared to the top deep learning models, according to the available experimental data. Findings validate the proposed hybrid design's provision of a strong and efficient","图像分类这一计算机视觉核心问题在多个特定领域均有应用。本文旨在探讨图像分类在现代技术与社会中的重要意义，以及其理念、方法和应用。许多计算机视觉系统依赖于图像分类，即根据图像所提供的信息，自动将图像归入预定义类别。本研究训练了一个混合深度学习系统，利用Caltech-256数据集高效识别图像。该系统同时采用了双向长短期记忆网络（Bidirectional Long Short-Term Memory, BiLSTM）和门控循环单元（Gated Recurrent Units, GRU）。数据集预处理包括标准化、标签编码、损坏图像识别和重复项去除。将数据集划分为训练集和测试集后，下一步是对二者分别进行特征提取。所提出的GRU+BiLSTM模型与AlexNet、MobileNetV2、EfficientNet和CNN模型在准确率（ACC）、精确率（PRE）、召回率（REC）和F1分数（F1）方面进行了对比评估。根据现有实验数据，与顶级深度学习模型相比，所提方法在ACC（98.9%）、PRE（99.1%）、REC（99.3%）和F1（100%）方面均表现更优。研究结果验证了所提出的混合设计提供了一种强大而高效的",null,"International Journal of Advanced Research in Science Communication and Technology","2026-09-11T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"通用计算机视觉图像分类论文，未涉及农业场景，与三农及农业信息化无直接关联，不建议入选。",[19],{"name":10,"url":6},[21,22,23],"农业人工智能","深度学习","图像识别","10.48175\u002Fijarsct-38253",{"doi":24,"openalex_id":26,"authors":27,"venue":10,"cited_by_count":15,"oa_url":6,"card":30,"direction":36,"ingested_from":37},"W7212235058",[28],{"name":29,"orcid":9},"Dr Chintal Kumar Patel",{"tldr":31,"method":32,"finding":33,"direction":34,"opportunity":35},"提出GRU+BiLSTM混合深度学习架构，在Caltech-256上实现高精度图像分类。","用Caltech-256数据集，结合GRU与BiLSTM，经预处理和特征提取后训","混合模型ACC达98.9%、F1达100%，优于AlexNet、MobileNetV2等对比模型。","农业人工智能与决策模型","可将该混合架构迁移至农业图像分类（如病虫害识别），验证跨域泛化与轻量化部署。","农业遥感与作物表型","openalex","2026-09-13T23:30:22.884557Z"]