A Deep Learning-based Dengue Mosquito Detection Method Using Faster R-CNN and Image Processing Techniques

Abstract

Dengue fever, a mosquito-borne disease caused by dengue viruses, is a significant public health concern in many countries especially in the tropical and subtropical regions. In this paper, we introduce a deep learning-based model using Faster R-CNN with InceptionV2 accompanied by image processing techniques to identify the dengue mosquitoes. Performance of the proposed model is evaluated using a custom mosquito dataset built upon varying environments which are collected from the internet. The proposed Faster R-CNN with InceptionV2 model is compared with other two state-of-art models, R-FCN with ResNet 101 and SSD with MobilenetV2. The False positive (FP), False negative (FN), precision and recall are used as performance measurement tools to evaluate the detection accuracy of the proposed model. The experimental results demonstrate that as a classifier the Faster- RCNN model shows 95.19% of accuracy and outperforms other state-of-the-art models as R-FCN and SSD model show 94.20% and 92.55% detection accuracy, respectively for the test dataset.

Deep Learning-Based Image Classification for Major Mosquito Species Inhabiting Korea

“…as a test set. Siddiqua et al [ 21 ] developed a dengue mosquito detection model using Inception V2 and Faster R-CNN and achieved a classification accuracy of 95.19%. Motta, D. et al [ 55 ] also applied the convolutional neural network for classification of dengue mosquitoes using CNN models such as LeNet, AlexNet, and GoogleNet, and the classification accuracy was 76.2%.…”

“…Goodwin et al [ 20 ] constructed an algorithm that utilized the Xception model to identify unlearned species. Siddiqua et al [ 21 ] used Inception V2 and faster R-CNN to detect dengue. To detect Aedes aegypti Linnaeus, 1762 and Aedes albopictus , a mosquito classification and detection technique was developed using AlexNet and a support vector machine (SVM), and the features of each body part were extracted [ 22 , 23 ].…”

“…In this study, we propose an automatic mosquito classification technique for identifying vector-borne mosquitoes in Republic of Korea. To develop this technique, a deep learning detection model was combined with Faster R-CNN [ 17 , 21 , 24 , 25 , 26 ] and Swin Transformer [ 27 ], which demonstrate the highest performance in object detection among the models. You Only Look Once (YOLO) v5 [ 28 ], ResNet DC-5 [ 29 ], ResNeXt 101 [ 30 ], and RetinaNet [ 31 ] were used to compare the performances of the mosquito detection models.…”

Real-Time Obstacle Detection with YOLOv8 in a WSN Using UAV Aerial Photography

“…Further, the proposed YOLOv8 exhibits a recall of 78.2%, a precision value of 89.99%, and a mAP of 87.4% when trained with 150 epochs. The testing performance of the proposed obstacle detection based on the YOLOv8 model is compared with the other existing object detection models, i.e., YOLOv7 [28], YOLOv5 [24], SSD [35], and Faster-RCNN [34]. The performance is analyzed for all classes with different iteration steps with our own datasets, as shown in Table 4.…”

“…Resizing an image means giving all of the images the same shape. Thus, the custom dataset with all images was resized to 800 × 600 pixels [33,34]. After that, the resized images were labeled according to the seven classes shown in Table 1.…”