Filters








700,340 Hits in 5.1 sec

A study on image-processing based identification of aspect ratio of coarse aggregate

Tianhua Li, Wenying Bai, Kejia Zhang, Zichao Pan, H. Li, M. Ashraf, O. Corbi, P. Yang, L. Wang, I. Corbi
2019 MATEC Web of Conferences  
In this paper, an image-processing based method is proposed to detect the aspect ratio of a polygonal aggregate. The procedure and used algorithms are demonstrated in detail.  ...  As an application, totally about 1000 coarse aggregates from the Xinjiang, China are selected to identify the aspect ratio.  ...  Some images of the selected aggregates are shown in Fig. 2. Fig. 2 . Images of selected aggregates.  ... 
doi:10.1051/matecconf/201927502007 fatcat:46pjxmqy7nhfhlky34zodgzv5m

Fast-At: Fast Automatic Thumbnail Generation Using Deep Neural Networks

Seyed A. Esmaeili, Bharat Singh, Larry S. Davis
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
It is a fully-convolutional deep neural network, which learns specific filters for thumbnails of different sizes and aspect ratios.  ...  The model generalizes to thumbnails of different sizes including those with extreme aspect ratios and can generate thumbnails in real time.  ...  The appropriate filter is decided based on the thumbnail aspect ratio. Figure 5 . 5 R-FCN and Fast-AT predictions on test set images.  ... 
doi:10.1109/cvpr.2017.445 dblp:conf/cvpr/EsmaeiliSD17 fatcat:mrj2v7q4uffnfo7z2iieg6g2wi

Fast-AT: Fast Automatic Thumbnail Generation using Deep Neural Networks [article]

Seyed A. Esmaeili, Bharat Singh, Larry S. Davis
2017 arXiv   pre-print
It is a fully-convolutional deep neural network, which learns specific filters for thumbnails of different sizes and aspect ratios.  ...  The model generalizes to thumbnails of different sizes including those with extreme aspect ratios and can generate thumbnails in real time.  ...  The appropriate filter is decided based on the thumbnail aspect ratio. Figure 5 . 5 R-FCN and Fast-AT predictions on test set images.  ... 
arXiv:1612.04811v2 fatcat:ndgajbj4zjhulp3tmd4k2mgq4i

Feature Selective Networks for Object Detection

Yao Zhai, Jingjing Fu, Yan Lu, Houqiang Li
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Our network produces the sub-region attention bank and aspect ratio attention bank for the whole image.  ...  The RoI-based sub-region attention map and aspect ratio attention map are selectively pooled from the banks, and then used to refine the original RoI features for RoI classification.  ...  For the RoIs of different aspect ratios, the aspect ratio attention map also produces distinct feature attentions. entire image.  ... 
doi:10.1109/cvpr.2018.00435 dblp:conf/cvpr/ZhaiF0L18 fatcat:7xtlg57kzrd23pkbzhwhfsfuxy

Feature Selective Networks for Object Detection [article]

Yao Zhai, Jingjing Fu, Yan Lu, Houqiang Li
2017 arXiv   pre-print
Our network produces the sub-region attention bank and aspect ratio attention bank for the whole image.  ...  The RoI-based sub-region attention map and aspect ratio attention map are selectively pooled from the banks, and then used to refine the original RoI features for RoI classification.  ...  Based on the detailed sub-region and aspect ratio information, distinctive attention maps are selected for each RoI and used to refine the original compacted RoI features.  ... 
arXiv:1711.08879v1 fatcat:pbcujnrc2bbyvpu6ueb4zrmt7u

Design Analysis of a High-Resolution Panoramic Camera Using Conventional Imagers and a Mirror Pyramid

Hong Hua, Narendra Ahuja, Chunyu Gao
2007 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Wide field of view (FOV) and high-resolution image acquisition is highly desirable in many vision-based applications.  ...  Using a dual mirror pyramid (DMP) panoramic camera as an example, in this paper, we examine how the pyramid geometry, and the selection and placement of imager clusters can be optimized to maximize the  ...  Imager orientation plays a critical role in affecting the aspect ratio and the aspect ratio is maximized at T ¼ 1 =2.  ... 
doi:10.1109/tpami.2007.33 pmid:17170487 fatcat:wurrx4zf5vfyjjde6o3rab4kby

A2S-Det: Efficiency Anchor Matching in Aerial Image Oriented Object Detection

Zhifeng Xiao, Kai Wang, Qiao Wan, Xiaowei Tan, Chuan Xu, Fanfan Xia
2020 Remote Sensing  
Object detection is a challenging task in aerial images, where many objects have large aspect ratios and are densely arranged.  ...  In this study, we propose an anchor selection method based on sample balance assigning anchors adaptively, which we name the Self-Adaptive Anchor Selection (A2S-Det) method.  ...  Unlike natural images, objects in aerial images may be densely arranged, in any direction and with large aspect ratios, which make it very challenging to precisely detect objects in aerial images.  ... 
doi:10.3390/rs13010073 fatcat:ixiqedig4fcdnfmqedanghm4r4

Slot Based Image Augmentation System for Object Detection [article]

Yingwei Zhou
2019 arXiv   pre-print
As the intrinsic feature of data-driven in deep learning, the first approach is "slot-based image augmentation" to enrich the dataset with extra foreground and background combinations.  ...  This proposed augmentation system has extra flexibility adapting to various scenarios and the performance-driven analysis provides an alternative aspect of conducting image augmentation  ...  Among those attributes, the instance area size, aspect ratio and category are applied as the filters to select candidates for slot substitution, in which the area size and aspect ratio are calculated in  ... 
arXiv:1907.12900v1 fatcat:4jx5ouk22fhstpto6exgxcxsd4

Learning to Learn Cropping Models for Different Aspect Ratio Requirements

Debang Li, Junge Zhang, Kaiqi Huang
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose a meta-learning (learning to learn) based aspect ratio specified image cropping method called Mars, which can generate cropping results of different expected aspect ratios.  ...  Specifically, the two meta-learners predict the parameters of the base model based on the given aspect ratio.  ...  First, we select N aspect ratios, each with a corresponding embedding vector. The set of selected aspect ratios is denoted as S τ , and the corresponding set of embedding vectors is S emb .  ... 
doi:10.1109/cvpr42600.2020.01270 dblp:conf/cvpr/LiZH20 fatcat:jworwmht45hehbueakfyggnwqi

Page 469 of SMPTE Motion Imaging Journal Vol. 105, Issue 8 [page]

1996 SMPTE Motion Imaging Journal  
Eisenstein went on to point out that cin- ema is based on dynamics.” It is easy to see why a dynamic image medium may elicit different aspect ratio preferences from those of a static image medium.  ...  Dynamic Image Aspect Ratio Preferences It has been stated that there is a pref- erence for wider aspect ratios in mov- ing image media, even if that means sacrificing resolution.”  ... 

PicWall: Photo collage on-the-fly

Zhipeng Wu, Kiyoharu Aizawa
2013 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference  
Given the expected canvas sizes, it tightly packs the input images while keeping their aspect ratios and orientations unchanged.  ...  Besides, various PicWall-based applications are also demonstrated. I. 4 JP Manga Reading Order Fig. 13 JP manga reading order V.S. general cartoon reading order.  ...  <leaf node> : select one image i from set L. The aspect ratio of i should best fit the arexp <leaf node> : select two image i, j from set L.  ... 
doi:10.1109/apsipa.2013.6694305 dblp:conf/apsipa/WuA13 fatcat:diw2s2u7mbfa3fdjiz264wopnu

Shape Oriented Feature Selection for Tomato Plant Identification

A. Hazra, K. Deb, S. Kundu, P. Hazra
2013 International Journal of Computer Applications Technology and Research  
By applying digital image processing techniques, tomato leaf and fruit images were pre-processed and morphological shape based features were computed.  ...  Next, supervised filter and wrapper based feature selection techniques were adopted to choose the optimal feature set leading to small within-class variance and large among-class distance which may be  ...  Perimeter Ratio Narrow Factor Linear Forward Floating Selection Aspect Ratio Perimeter Ratio Narrow Factor Figure 11 -Most relevant features selected for Tomato Leaf/Fruiting Habit Data  ... 
doi:10.7753/ijcatr0204.1011 fatcat:lrdpekehojbcrfbdfhlma7lney

Indexing, Learning and Content-Based Retrieval for Special Purpose Image Databases [chapter]

Mark J. Huiskes, Eric J. Pauwels
2005 Advances in Computers  
purpose image databases  ...  C e n t r u m v o o r W i s k u n d e e n I n f o r m a t i c a PNA Probability, Networks and Algorithms Probability, Networks and Algorithms Indexing, learning and content-based retrieval for special  ...  Given that an aspect is relevant, we expect that a few, sayÑ + , of the n + selected positive images have been chosen based to some extent on this aspect.  ... 
doi:10.1016/s0065-2458(05)65005-x fatcat:qdnxzbdaozbdxavfkvo5yui5ra

Robust Character Recognition Using Adaptive Feature Extraction Method

Minoru MORI, Minako SAWAKI, Junji YAMATO
2010 IEICE transactions on information and systems  
This estimation enables us to compensate the aspect ratio associated with shape and the degradation in feature values and so obtain higher recognition accuracy.  ...  This paper describes an adaptive feature extraction method that exploits category-specific information to overcome both image degradation and deformation in character recognition.  ...  In addition, although geometric features are more robust against deformation than image-based template matching, they are not invariant for deformation such as aspect ratio fluctuation and stroke position  ... 
doi:10.1587/transinf.e93.d.125 fatcat:t2nvwjowunfl5oi47vplncpbqa

Creation and luminescence of size-selected gold nanorods

Y. Chen, Y. Zhang, D. J. S. Birch, A. S. Barnard
2012 Nanoscale  
In this work, we produce stable size-selected gold nanorods (aspect ratio 1-2) using a size-selected cluster source and correlate their luminescence behaviour with the particle shape.  ...  Thermodynamic modelling is used to predict the preferred aspect ratio of 1.5, in agreement with the observations, and confirms that the double-icosahedron observed in experiments is significantly lower  ...  The particle number reduces with the increase in the aspect ratio; nevertheless, elongated particles with aspect ratio larger than 2 are observed.  ... 
doi:10.1039/c2nr30324h pmid:22766744 fatcat:isky4qwgmveyzbrw4qdjexgetm
« Previous Showing results 1 — 15 out of 700,340 results