The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Road pixel segmentation in airborne data is an important and challenging task. Recently, a sophisticated and robust approach based on superpixels and minimum cost paths has been published. In order to find out which of the numerous features are most essential, we propose a forward-search wrapper approach for feature selection which was tested with two different classifiers and with both generic and...
In this paper we propose a deep learning technique to improve the performance of semantic segmentation tasks. Previously proposed algorithms generally suffer from the over-dependence on a single modality as well as a lack of training data. We made three contributions to improve the performance. Firstly, we adopt two models which are complementary in our framework to enrich field-of-views and features...
Object part segmentation is a challenging and fundamental problem in computer vision. Its difficulties may be caused by the varying viewpoints, poses, and topological structures, which can be attributed to an essential reason, i.e., a specific object is a 3D model rather than a 2D figure. Therefore, we conjecture that not only 2D appearance features but also 3D geometric features could be helpful...
In this paper we propose a new salient object detection method via structured label prediction. By learning appearance features in rectangular regions, our structural region representation encodes the local saliency distribution with a matrix of binary labels. We show that the linear combination of structured labels can well model the saliency distribution in local regions. Representing region saliency...
Recently, CNN-based models have achieved remarkable success in image-based salient object detection (SOD). In these models, a key issue is to find a proper network architecture that best fits for the task of SOD. Toward this end, this paper proposes two-stream fixation-semantic CNNs, whose architecture is inspired by the fact that salient objects in complex images can be unambiguously annotated by...
This paper proposes a deep learning architecture based on Residual Network that dynamically adjusts the number of executed layers for the regions of the image. This architecture is end-to-end trainable, deterministic and problem-agnostic. It is therefore applicable without any modifications to a wide range of computer vision problems such as image classification, object detection and image segmentation...
One of recent trends [31, 32, 14] in network architecture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more efficient than a large kernel, given the same computational complexity. However, in the field of semantic segmentation, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive...
In this paper we propose a deep learning architecture to make the best use of global and local information for pixel-wise semantic segmentation. The architecture of three-skips CNN is built with convolutional layers in VGG16 network and its mirrored convolutional layers. Our architecture aims to road scene understanding. In order to save memory and computational time, we use unpooling layers to map...
Saliency detection aims to highlight the most relevant objects in an image. Methods using conventional models struggle whenever salient objects are pictured on top of a cluttered background while deep neural nets suffer from excess complexity and slow evaluation speeds. In this paper, we propose a simplified convolutional neural network which combines local and global information through a multi-resolution...
We propose a novel data-driven approach for automatically detecting and completing gaps in line drawings with a Convolutional Neural Network. In the case of existing inpainting approaches for natural images, masks indicating the missing regions are generally required as input. Here, we show that line drawings have enough structures that can be learned by the CNN to allow automatic detection and completion...
This paper proposes a deep architecture for saliency detection by fusing pixel-level and superpixel-level predictions. Different from the previous methods that either make dense pixellevel prediction with complex networks or region-level prediction for each region with fully-connected layers, this paper investigates an elegant route to make two-level predictions based on a same simple fully convolutional...
Magnetic flux leakage (MFL) inspection is one of the most commonly used nondestructive testing (NDE) technologies. This paper proposes a novel method for classifying the MFL response segments based on convolution neural network (CNN). In order to skip the procedure of saving the normalized MFL segment and save some computing time, a normalization layer is added to the proposed model. Moreover, the...
This paper investigates the problem of weakly-supervised semantic segmentation, where image-level labels are used as weak supervision. Inspired by the successful use of Convolutional Neural Networks (CNNs) for fully-supervised semantic segmentation, we choose to directly train the CNNs over the oversegmented regions of images for weakly-supervised semantic segmentation. Although there are a few studies...
Single sperm detection and tracking has received increasing attentions since In Vitro Fertilization (IVF) and Intracytoplasmic Sperm Injection (ICSI) techniques were introduced. In this paper, we proposed an automated system to extract and track single sperm movement. Intersect Cortical Model (ICM) which is derived from Pulse Coupled Neural Network (PCNN) is employed to extract region coordinates...
Style transfer is an important task in which the style of a source image is mapped onto that of a target image. The method is useful for synthesizing derivative works of a particular artist or specific painting. This work considers targeted style transfer, in which the style of a template image is used to alter only part of a target image. For example, an artist may wish to alter the style of only...
Video Summarization plays a vital role in the internet user's life, especially for those searching for user specified video of interest for a long time. In order to provide support for users in terms of searching and retrieving video content, it is necessary to segment the video into shots and extract representative frame of each shot which acts as a summary of the video. So, in this paper, an approach...
The basic components of chemical expressions and its corresponding reactions are chemical symbols and structures. To recognize a handwritten or printed chemical expression, proper identification of the chemical symbols and structures are important. This paper has reviewed the existing algorithms and models used for identifying the organic chemical structures. The objective of this paper is to find...
Various applications have been developed during recent years which are based on the computer vision system. In this field, plant species recognition is a challenging task for researchers due to environmental and image acquisition condition of image. Leaf classification application can be used for various purpose such as remote sensing imaging, botanical characteristically analysis etc. Now a day,...
In this paper, we generated an activity recognition model using an ANN and trained it using Backpropagation learning. We considered a sandwich making scenario and identified the hand-motion-based activities of reaching, sprinkling, spreading and cutting. The contribution of this paper is twofold: First, given the fact that many image processing steps like feature identification are computation intensive...
Deep learning had a significant impact on diverse pattern recognition tasks in the recent past. In this paper, we investigate its potential for keyword spotting in handwritten documents by designing a novel feature extraction system based on Convolutional Deep Belief Networks. Sliding window features are learned from word images in an unsupervised manner. The proposed features are evaluated both for...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.