Retinal Blood Vessel Extraction Using a New Enhancement Technique of Modified Convolution Filters and Sauvola Thresholding

The retinal blood vessels in humans are major components with different shapes and sizes. The extraction of the blood vessels from the retina is an important step to identify the type or nature of the pattern of the diseases in the retina. Furthermore, the retinal blood vessel was also used for diagnosis, detection, and classification. The most recent solution in this topic is to enable retinal image improvement or enhancement by a convolution filter and Sauvola threshold. In image enhancement, gamma correction is applied before filtering the retinal fundus. After that, the image should be transformed to a gray channel to enhance pictorial clarity using contrast-limited histogram equalization. For filter, this paper combines two convolution filters, namely sharpen and smooth filters. The Sauvola threshold, the morphology, and the medium filter are applied to extract blood vessels from the retinal image. This paper uses DRIVE and STARE datasets. The accuracies of the proposed method are 95.37% for DRIVE with a runtime of 1.77[Formula: see text]s and 95.17% for STARE with 2.05[Formula: see text]s runtime. Based on the result, it concludes that the proposed method is good enough to achieve average calculation parameters of a low time quality, quick, and significant.

Combining Learnable Low-dimensional Binary Filter Bases for Compressing Convolutional Neural Networks

Existing convolutional neural networks (CNNs) have achieved significant performance on various real-life tasks, but a large number of parameters in convolutional layers requires huge storage and computation resources which makes it difficult to deploy CNNs on memory-constraint embedded devices. In this paper, we propose a novel compression method that generates the convolution filters in each layer by combining a set of learnable low-dimensional binary filter bases. The proposed method designs more compact convolution filters by stacking the linear combinations of these filter bases. Because of binary filters, the compact filters can be represented using less number of bits so that the network can be highly compressed. Furthermore, we explore the sparsity of coefficient through L1-ball projection when conducting linear combination to avoid overfitting. In addition, we analyze the compression performance of the proposed method in detail. Evaluations on four benchmark datasets under VGG-16 and ResNet-18 structures show that the proposed method can achieve a higher compression ratio with comparable accuracy compared with the existing state-of-the-art filter decomposition and network quantization methods.

Combining Learnable Low-dimensional Binary Filter Bases for Compressing Convolutional Neural Networks

Existing convolutional neural networks (CNNs) have achieved significant performance on various real-life tasks, but a large number of parameters in convolutional layers requires huge storage and computation resources which makes it difficult to deploy CNNs on memory-constraint embedded devices. In this paper, we propose a novel compression method that generates the convolution filters in each layer by combining a set of learnable low-dimensional binary filter bases. The proposed method designs more compact convolution filters by stacking the linear combinations of these filter bases. Because of binary filters, the compact filters can be represented using less number of bits so that the network can be highly compressed. Furthermore, we explore the sparsity of coefficient through L1-ball projection when conducting linear combination to avoid overfitting. In addition, we analyze the compression performance of the proposed method in detail. Evaluations on four benchmark datasets under VGG-16 and ResNet-18 structures show that the proposed method can achieve a higher compression ratio with comparable accuracy compared with the existing state-of-the-art filter decomposition and network quantization methods.

A Precision Agricultural Application: Manggis Fruit Classification Using Hybrid Deep Learning

Fruits come in different variants and subspecies. While some subspecies of fruits can be easily differentiated, others may require an expertness to differentiate them. Although farmers rely on the traditional methods to identify and classify fruit types, the methods are prone to so many challenges. Training a machine to identify and classify fruit types in place of traditional methods can ensure precision fruit classification. By taking advantage of the state-of-the-art image recognition techniques, we approach fruits classification from another perspective by proposing a high performing hybrid deep learning which could ensure precision mangosteen fruit classification. This involves a proposed optimized Convolutional Neural Network (CNN) model compared to other optimized models such as Xception, VGG16, and ResNet50 using Adam, RMSprop, Adagrad, and Stochastic Gradient Descent (SGD) optimizers on specified dense layers and filters numbers. The proposed CNN model has three types of layers that make up its model, they are: 1) the convolutional layers, 2) the pooling layers, and 3) the fully connected (FC) layers. The first convolution layer uses convolution filters with a filter size of 3x3 used for initializing the neural network with some weights prior to updating to a better value for each iteration. The CNN architecture is formed from stacking these layers. Our self-acquired dataset which is composed of four different types of Malaysian mangosteen fruit, namely Manggis Hutan, Manggis Mesta, Manggis Putih and Manggis Ungu was employed for the training and testing of the proposed CNN model. The proposed CNN model achieved 94.99% classification accuracy higher than the optimized Xception model which achieved 90.62% accuracy in the second position.

Image Steganalysis via Diverse Filters and Squeeze-and-Excitation Convolutional Neural Network

Steganalysis is a method to detect whether the objects contain secret messages. With the popularity of deep learning, using convolutional neural networks (CNNs), steganalytic schemes have become the chief method of combating steganography in recent years. However, the diversity of filters has not been fully utilized in the current research. This paper constructs a new effective network with diverse filter modules (DFMs) and squeeze-and-excitation modules (SEMs), which can better capture the embedding artifacts. As the essential parts, combining three different scale convolution filters, DFMs can process information diversely, and the SEMs can enhance the effective channels out from DFMs. The experiments presented that our CNN is effective against content-adaptive steganographic schemes with different payloads, such as S-UNIWARD and WOW algorithms. Moreover, some state-of-the-art methods are compared with our approach to demonstrate the outstanding performance.

Flat morphological operators from non-increasing set operators, I: general theory

Flat morphology is a general method for obtaining increasing operators on grey-level or multivalued images from increasing operators on binary images (or sets). It relies on threshold stacking and superposition; equivalently, Boolean max and min operations are replaced by lattice-theoretical sup and inf operations. In this paper we consider the construction a flat operator on grey-level or colour images from an operator on binary images that is not increasing. Here grey-level and colour images are functions from a space to an interval in ℝ m or ℤ m (m ≥ 1). Two approaches are proposed. First, we can replace threshold superposition by threshold summation. Next, we can decompose the non-increasing operator on binary images into a linear combination of increasing operators, then apply this linear combination to their flat extensions. Both methods require the operator to have bounded variation, and then both give the same result, which conforms to intuition. Our approach is very general, it can be applied to linear combinations of flat operators, or to linear convolution filters. Our work is based on a mathematical theory of summation of real-valued functions of one variable ranging in a poset. In a second paper, we will study some particular properties of non-increasing flat operators.

A CONVblock for Convolutional Neural Networks

The reduction in the size of convolution filters has been shown to be effective in image classification models. They make it possible to reduce the calculation and the number of parameters used in the operations of the convolution layer while increasing the efficiency of the representation. The authors present a deep architecture for classification with improved performance. The main objective of this architecture is to improve the main performances of the network thanks to a new design based on CONVblock. The proposal is evaluated on a classification database: CIFAR-10 and MNIST. The experimental results demonstrate the effectiveness of the proposed method. This architecture offers an error of 1.4% on CIFAR-10 and 0.055% on MNIST.