JOINT IMAGE SEGMENTATION AND CLASSIFICATION WITH APPLICATION TO CLUTTERED CORAL IMAGES

In this paper, we propose a Pixel-Training Image-Testing (PTIT) algorithm for joint object segmentation and classification. PTIT consists of four processing stages: sample-pixel (human) labeling, pixel-wise training, image generalization and uniform region refinement. Compared to the state-of-the-art semantic image segmentation and classification algorithms, PTIT significantly reduces the time required for labeling and is capable of handling more complex scenes (cluttered background and large amount of objects of interest). PTIT performance is tested on coral images to show its advantage over the typical segmentation followed by classification image processing framework. For visual analysis, our algorithmically derived class shows class structure better, while also displaying most of time better receiver operating character at the pixel level.

[1]  J.A. Diaz,et al.  Classification of Underwater Color Images with Applications in the Study of Deep Coral Reefs , 2006, 2006 49th IEEE International Midwest Symposium on Circuits and Systems.

[2]  S. Kumar,et al.  Segmentation and Classification of Coral for Oceanographic Surveys: A Semi-Supervised Machine Learning Approach , 2006, OCEANS 2006 - Asia Pacific.

[3]  Tao Mei,et al.  Deep Collaborative Embedding for Social Image Understanding , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[5]  Shengcai Liao,et al.  Learning Multi-scale Block Local Binary Patterns for Face Recognition , 2007, ICB.

[6]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[7]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[8]  P. C. Naval,et al.  Coral Identification Information System , 2013, 2013 IEEE International Underwater Technology Symposium (UT).

[9]  Vijanth S. Asirvadam,et al.  Color Space Selection for Color Image Enhancement Applications , 2009, 2009 International Conference on Signal Acquisition and Processing.

[10]  Luca Maria Gambardella,et al.  Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images , 2012, NIPS.

[11]  Robert B. Halley,et al.  GIS compilation of data collected from the Pulley Ridge Deep Coral Reef region , 2005 .

[12]  Xinge You,et al.  Single image rain streaks removal based on self-learning and structured sparse representation , 2015, 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP).

[13]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  O. Pizarro,et al.  Stereoscopic imaging for coral segmentation and classification , 2006, OCEANS 2006.

[16]  Kevin E. Kohler,et al.  Coral Point Count with Excel extensions (CPCe): A Visual Basic program for the determination of coral and substrate coverage using random point count methodology , 2006, Comput. Geosci..

[17]  B. S. Manjunath,et al.  Unsupervised Segmentation of Color-Texture Regions in Images and Video , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Jinhui Tang,et al.  Weakly Supervised Deep Matrix Factorization for Social Image Understanding , 2017, IEEE Transactions on Image Processing.