Exploiting SIFT Descriptor for Rotation Invariant Convolutional Neural Network
This paper presents a novel approach to exploit the distinctive invariant features in convolutional neural network. The proposed CNN model uses Scale Invariant Feature Transform (SIFT) descriptor instead of the max-pooling layer. Max-pooling layer discards the pose, i.e., translational and rotational relationship between the low-level features, and hence unable to capture the spatial hierarchies between low and high level features. The SIFT descriptor layer captures the orientation and the spatial relationship of the features extracted by convolutional layer. The proposed SIFT Descriptor CNN therefore combines the feature extraction capabilities of CNN model and rotation invariance of SIFT descriptor. Experimental results on the MNIST and fashionMNIST datasets indicates reasonable improvements over conventional methods available in literature.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Dense Segmentation-Aware Descriptors
In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes. For this, we downplay measurements coming from areas that are unlikely to belong to t…
Motion EstimationSegmentationPerformance Evalution of 3D Keypoint Detectors and Descriptors for Plants Health Classification
Plant Phenomics based on imaging based techniques can be used to monitor the health and the diseases of plants and crops. The use of 3D data for plant phenomics is a recent phenomenon. However, since 3D point cloud conta…
General ClassificationA proposition of a robust system for historical document images indexation
Characterizing noisy or ancient documents is a challenging problem up to now. Many techniques have been done in order to effectuate feature extraction and image indexation for such documents. Global approaches are in gen…
Content-Based Image Retrieval Based on Late Fusion of Binary and Local Descriptors
One of the challenges in Content-Based Image Retrieval (CBIR) is to reduce the semantic gaps between low-level features and high-level semantic concepts. In CBIR, the images are represented in the feature space and the p…
Content-Based Image RetrievalImage RetrievalRetrievalTranslationPerformance Evaluation of SIFT Descriptor against Common Image Deformations on Iban Plaited Mat Motifs
Borneo indigenous communities are blessed with rich craft heritage. One such examples is the Iban's plaited mat craft. There have been many efforts by UNESCO and the Sarawak Government to preserve and promote the craft. …