V. C. Swetha
Bio: V. C. Swetha is an academic researcher from Indian Institute of Space Science and Technology. The author has contributed to research in topics: MNIST database & Pattern recognition (psychology). The author has an hindex of 1, co-authored 2 publications receiving 1 citations.
18 Dec 2018
TL;DR: It is demonstrated how the basic PCA based rotation and scale invariant image recognition can be integrated to CNN for achieving better rotational and scale invariances in classification.
Abstract: Last decade has witnessed rapid growth for the popularity of Convolutional Neural Networks (CNNs), in detecting and classifying objects. The self trainable nature of CNNs makes them the strongest candidate as a classifier and a feature extractor. However, many of the existing CNN architectures fail recognizing texts or objects under input rotation and scaling. This paper introduces an elegant approach, 'Scale and Rotation Corrected CNN (SRC-CNN)' for scale and rotation invariant text recognition, exploiting the concept of principal component of characters. Prior to training and testing with baseline CNN, 'SRC-CNN' maps each character image to a reference orientation and scale, which is again derived from the character image itself. SRC-CNN is capable of recognizing characters in a document, even though they differ in orientation and scale greatly. The proposed method does not demand any training with samples which are scaled or rotated. The performance of proposed approach is validated on different character data sets like MNIST, MNIST_rot_12k and English alphabets and compared with state of the art rotation invariant classification networks. SRC-CNN is a generalized approach and can be extended for rotation and scale invariant classification of many other datasets as well, choosing any appropriate baseline CNN. Here we have demonstrated the generality of the proposed SRC-CNN on MNIST Fashion data set and found to perform well in rotation and scale invariant classification of objects as well. This paper demonstrates how the basic PCA based rotation and scale invariant image recognition can be integrated to CNN for achieving better rotational and scale invariances in classification.
••01 Jan 2020
TL;DR: The approach ‘Eigenvector Orientation Corrected LeNet (EOCL)’ presents a simple method to make ordinary LeNet capable of detecting rotated digits, and also to predict the relative angle of orientation of digits with unknown orientation.
Abstract: Convolutional Neural Networks (CNNs) are being used popularly for detecting and classifying objects. Rotational invariance is not guaranteed by many of the existing CNN architectures. Many attempts have been made to acquire rotational invariance in CNNs. Our approach ‘Eigenvector Orientation Corrected LeNet (EOCL)’ presents a simple method to make ordinary LeNet  capable of detecting rotated digits, and also to predict the relative angle of orientation of digits with unknown orientation. The proposed method does not demand any modification in the existing LeNet architecture, and requires training with digits having only single orientation. EOCL incorporates an ‘orientation estimation and correction’ step prior to the testing phase. Using Principal Component Analysis, we find the maximum spread direction (Principal Component) of each test sample and then align it vertically. We demonstrate the improvement in classification accuracy and reduction in test time achieved by our approach, on rotated-MNIST  and MNIST_rot_12k test datasets, compared to other existing methods.
01 Jan 2023
TL;DR: In this article , the adaptive Neuro-Fuzzy Inference System (ANFIS) was used to classify the mammogram images into normal, benign, and malignant types.
Abstract: Every year, the number of women affected by breast tumors is increasing worldwide. Hence, detecting and segmenting the cancer regions in mammogram images is important to prevent death in women patients due to breast cancer. The conventional methods obtained low sensitivity and specificity with cancer region segmentation accuracy. The high-resolution standard mammogram images were supported by conventional methods as one of the main drawbacks. The conventional methods mostly segmented the cancer regions in mammogram images concerning their exterior pixel boundaries. These drawbacks are resolved by the proposed cancer region detection methods stated in this paper. The mammogram images are classified into normal, benign, and malignant types using the Adaptive Neuro-Fuzzy Inference System (ANFIS) approach in this paper. This mammogram classification process consists of a noise filtering module, spatial-frequency transformation module, feature computation module, and classification module. The Gaussian Filtering Algorithm (GFA) is used as the pixel smooth filtering method and the Ridgelet transform is used as the spatial-frequency transformation module. The statistical Ridgelet feature metrics are computed from the transformed coefficients and these values are classified by the ANFIS technique in this paper. Finally, Probability Histogram Segmentation Algorithm (PHSA) is proposed in this work to compute and segment the tumor pixels in the abnormal mammogram images. This proposed breast cancer detection approach is evaluated on the mammogram images in MIAS and DDSM datasets. From the extensive analysis of the proposed tumor detection methods stated in this work with other works, the proposed work significantly achieves a higher performance. The methodologies proposed in this paper can be used in breast cancer detection hospitals to assist the breast surgeon to detect and segment the cancer regions.
TL;DR: In this paper, the watershed algorithm was used for marker-driven segmentation of corneal endothelial cells and an encoder-decoder convolutional neural network trained in a sliding window set up to predict the probability of cell centers (markers) and cell borders.
Abstract: Quantitive information about corneal endothelium cells’ morphometry is vital for assessing cornea pathologies. Nevertheless, in clinical, everyday routine dominates qualitative assessment based on visual inspection of the microscopy images. Although several systems exist for automatic segmentation of corneal endothelial cells, they exhibit certain limitations. The main one is sensitivity to low contrast and uneven illumination, resulting in over-segmentation. Subsequently, image segmentation results often require manual editing of missing or false cell edges. Therefore, this paper further investigates the problem of corneal endothelium cell segmentation. A fully automatic pipeline is proposed that incorporates the watershed algorithm for marker-driven segmentation of corneal endothelial cells and an encoder-decoder convolutional neural network trained in a sliding window set up to predict the probability of cell centers (markers) and cell borders. The predicted markers are used for watershed segmentation of edge probability maps outputted by a neural network. The proposed method's performance on a heterogeneous dataset comprising four publicly available corneal endothelium image datasets is analyzed. The performance of three convolutional neural network models (i.e., U-Net, SegNet, and W-Net) incorporated in the proposed pipeline is examined. The results of the proposed pipeline are analyzed and compared to the state-of-the-art competitor. The obtained results are promising. Regardless of the convolutional neural model incorporated into the proposed pipeline, it notably outperforms the competitor. The proposed method scored 97.72% of cell detection accuracy, compared to 87.38% achieved by the competitor. The advantage of the introduced method is also apparent for cell size, DICE coefficient, and Modified Hausdorff distance.
TL;DR: This paper presents a deep image restoration model that restores adversarial examples so that the target model is classified correctly again and proves that its results are better than other rival methods.
Abstract: These days, deep learning and computer vision are much-growing fields in this modern world of information technology. Deep learning algorithms and computer vision have achieved great success in different applications like image classification, speech recognition, self-driving vehicles, disease diagnostics, and many more. Despite success in various applications, it is found that these learning algorithms face severe threats due to adversarial attacks. Adversarial examples are inputs like images in the computer vision field, which are intentionally slightly changed or perturbed. These changes are humanly imperceptible. But are misclassified by a model with high probability and severely affects the performance or prediction. In this scenario, we present a deep image restoration model that restores adversarial examples so that the target model is classified correctly again. We proved that our defense method against adversarial attacks based on a deep image restoration model is simple and state-of-the-art by providing strong experimental results evidence. We have used MNIST and CIFAR10 datasets for experiments and analysis of our defense method. In the end, we have compared our method to other state-ofthe-art defense methods and proved that our results are better than other rival methods.
TL;DR: The current mainstream one-stage object detection model is summarized, and based on YOLOv1, it is continuously optimized, and the improvements and shortcomings are summarized in detail.
Abstract: As a popular research direction in computer vision, deep learning technology has promoted breakthroughs in the field of object detection. In recent years, the combination of object detection and the Internet of Things (IoT) has been widely used in the fields of face recognition, pedestrian detection, unmanned driving, and customs detection. With the development of object detection, two different detection algorithms, one-stage, and two-stage have gradually formed. This paper mainly introduces the one-stage object detection algorithm. Firstly, the development process of the convolutional neural network is briefly reviewed, Then, the current mainstream one-stage object detection model is summarized. Based on YOLOv1, it is continuously optimized, and the improvements and shortcomings are summarized in detail. Finally, a summary is made based on the difficulties and challenges of one-stage object detection algorithms. Abstract