Region Of Interest Feature Extraction Research Articles

BFF R-CNN: Balanced Feature Fusion for Object Detection

In the neck part of a two-stage object detection network, feature fusion is generally carried out in either a top-down or bottom-up manner. However, two types of imbalance may exist: feature imbalance in the neck of the model and gradient imbalance in the region of interest extraction layer due to the scale changes of objects. The deeper the network is, the more abstract the learned features are, that is to say, more semantic information can be extracted. However, the extracted image background, spatial location, and other resolution information are less. In contrast, the shallow part can learn little semantic information, but a lot of spatial location information. We propose the Both Ends to Centre to Multiple Layers (BEtM) feature fusion method to solve the feature imbalance problem in the neck and a Multi-level Region of Interest Feature Extraction (MRoIE) layer to solve the gradient imbalance problem. In combination with the Region-based Convolutional Neural Network (R-CNN) framework, our Balanced Feature Fusion (BFF) method offers significantly improved network performance compared with the Faster R-CNN architecture. On the MS COCO 2017 dataset, it achieves an average precision (AP) that is 1.9 points and 3.2 points higher than those of the Feature Pyramid Network (FPN) Faster R-CNN framework and the Generic Region of Interest Extractor (GRoIE) framework, respectively.

Reinforced Neighbour Feature Fusion Object Detection with Deep Learning

Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, previous works have tried to improve the performance in various object detection necks but have failed to extract features efficiently. To solve the insufficient features of objects, this work introduces some of the most advanced and representative network models based on the Faster R-CNN architecture, such as Libra R-CNN, Grid R-CNN, guided anchoring, and GRoIE. We observed the performance of Neighbour Feature Pyramid Network (NFPN) fusion, ResNet Region of Interest Feature Extraction (ResRoIE) and the Recursive Feature Pyramid (RFP) architecture at different scales of precision when these components were used in place of the corresponding original members in various networks obtained on the MS COCO dataset. Compared to the experimental results after replacing the neck and RoIE parts of these models with our Reinforced Neighbour Feature Fusion (RNFF) model, the average precision (AP) is increased by 3.2 percentage points concerning the performance of the baseline network.

3D image recognition using new set of fractional-order Legendre moments and deep neural networks

3D Image representation is an important topic in computer vision and pattern recognition. Recently, 3D image analysis by fractional-order orthogonal moments has provided a new research direction, which has prompted researchers to think about efficient and fast classification. In this paper, the authors derived novel sets of fractional-order Legendre moment invariants (FrLMIs), for 3D object description and recognition. Therefore, an analysis of the performance of reconstruction and classification based on fractional-order moment invariants and Deep Neural Networks (DNNs) by changing the number of descriptors was presented. Accordingly, the performance of these proposed fractional-order moments and moment invariants are evaluated through several appropriate experiments, including 3D image reconstruction, region of interest feature extraction, invariance with respect to the geometric transformations and noisy, and 3D Object classification using different fractional parameters. The superiority of the proposed method is verified by comparing the classification percentages obtained by varying the amount of data used during the training process in comparison with the existing methods. The work presented will help to create new neural network architectures that take advantage of the descriptive capacity of 3D fractional-order moments. Finally, these fractional-order moments are very fast and computationally inexpensive which could be useful in many computer vision applications. Based on these characteristics, the proposed FrOLMs and FrLMIs outperformed all existing orthogonal moments.