Attention-Guided Efficientnet Architecture For Precise Criminal Identification in Surveillance Images
2026-07-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors address the problem of recognizing criminals from blurry and low-quality surveillance images, which is hard due to factors like poor lighting and face angles. They created a new method called AG-EfficientNet that combines a special neural network, EfficientNet-B0, with attention modules to better focus on important facial features. They also use ways to mix different levels of detail and optimize the learning to distinguish different faces clearly. Testing on known face datasets showed their method works better than other popular networks. Their analysis also confirmed that the attention approach helps the system learn useful features for recognizing faces.
EfficientNet-B0Convolutional Block Attention Modules (CBAM)Face recognitionSurveillance imageryMulti-scale feature fusionSoftmax-Triplet lossLabeled Faces in the Wild (LFW)SCFace datasetGrad-CAM visualizationDeep learning architectures
Authors
Savitha N J, Lata B T
Abstract
Criminal identification from surveillance imagery has become a critical research area in intelligent forensic surveillance systems due to the increasing deployment of CCTV cameras in public and private environments. However, surveillance-based face recognition remains highly challenging because of low image resolution, illumination variation, motion blur, pose changes, facial occlusion, and background clutter. To address these limitations, this paper proposes an Attention-Guided EfficientNet (AG-EfficientNet) framework for precise criminal identification in surveillance images. The proposed framework integrates EfficientNet-B0 with Convolutional Block Attention Modules (CBAM) to enhance discriminative facial feature learning under degraded surveillance conditions. In addition, a multi-scale surveillance feature fusion strategy is introduced to preserve both local texture information and high-level semantic identity representations. A hybrid Softmax-Triplet optimization mechanism is further employed to improve inter-class separability and intra-class compactness for robust criminal identity discrimination. The proposed framework was experimentally evaluated using the Labeled Faces in the Wild (LFW) and SCFace datasets. Experimental results demonstrate that the proposed AG-EfficientNet framework achieved superior surveillance recognition performance with an identification accuracy of 98.2%, Precision of 97.9%, Recall of 97.6%, F1-Score of 97.7%, and ROC-AUC of 0.99, outperforming conventional deep learning architectures including AlexNet, VGG16, ResNet50, MobileNetV2, and standard EfficientNet-B0. Furthermore, Grad-CAM visualization and ablation analysis confirm the effectiveness of the proposed attention-guided feature learning strategy.