Abstract
The input to a machine learning model is a one-dimensional feature vector. However, in recent learning models, such as convolutional and recurrent neural networks, two- and three-dimensional feature tensors can also be inputted to the model. During training, the machine adjusts its internal parameters to project each feature tensor close to its target. After training, the machine can be used to predict the target for previously unseen feature tensors. What this study focuses on is the requirement that feature tensors must be of the same size. In other words, the same number of features must be present for each sample. This creates a barrier in processing images and texts, as they usually have different sizes, and thus different numbers of features. In classifying an image using a convolutional neural network (CNN), the input is a three-dimensional tensor, where the value of each pixel in each channel is one feature. The three-dimensional feature tensor must be the same size for all images. However, images are not usually of the same size and so are not their corresponding feature tensors. Resizing images to the same size without deforming patterns contained therein is a major challenge. This study proposes zero-padding for resizing images to the same size and compares it with the conventional approach of scaling images up (zooming in) using interpolation. Our study showed that zero-padding had no effect on the classification accuracy but considerably reduced the training time. The reason is that neighboring zero input units (pixels) will not activate their corresponding convolutional unit in the next layer. Therefore, the synaptic weights on outgoing links from input units do not need to be updated if they contain a zero value. Theoretical justification along with experimental endorsements are provided in this paper.
Highlights
Convolutional neural network (CNN) has recently outperformed other neural network architectures, machine learning, and image processing approaches in image classification [6, 46, 50, 56, 58] due to its independence from hand-crafted visual features and excellent abstract and semantic abilities [58]
Since the emergence of CNNs and their staggering success in image classification, many attempts have been made by researchers to improve their accuracy and time performance
One aspect that has not witnessed much attention is the strict requirement of CNNs in receiving images of the same size
Summary
Convolutional neural network (CNN) has recently outperformed other neural network architectures, machine learning, and image processing approaches in image classification [6, 46, 50, 56, 58] due to its independence from hand-crafted visual features and excellent abstract and semantic abilities [58]. A CNN consists of convolutional layers followed by fully-connected layers (Fig. 1). A convolutional layer consists of a convolution filter, followed by a pooling filter and an activation function. A convolution filter has a number (n) of filters, with the same window size (f), sweeping over the image with a stride of sf. Pooling summarizes the outputs of neighboring groups of neurons in the same kernel map. A pooling layer has a window with the size of p that sweeps over the image with a stride of sp. The last fully-connected layer in CNN has as many neurons as the number of classes. Among the model’s hyperparameters are n, f, sf, p, sp and the number of neurons in fully-connected layers
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
