Flower classification using deep convolutional neural networks

Flower classification is a challenging task due to the wide range of flower species, which have a similar shape, appearance or surrounding objects such as leaves and grass. In this study, the authors propose a novel two-step deep learning classifier to distinguish flowers of a wide range of species. First, the flower region is automatically segmented to allow localisation of the minimum bounding box around it. The proposed flower segmentation approach is modelled as a binary classifier in a fully convolutional network framework. Second, they build a robust convolutional neural network classifier to distinguish the different flower types. They propose novel steps during the training stage to ensure robust, accurate and real-time classification. They evaluate their method on three well known flower datasets. Their classification results exceed 97% on all datasets, which are better than the state-of-the-art in this domain.

[1]  Xiaoling Xia,et al.  Inception-v3 for flower classification , 2017, 2017 2nd International Conference on Image, Vision and Computing (ICIVC).

[2]  Takeshi Saitoh,et al.  Automatic recognition of blooming flowers , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Qi Tian,et al.  Image Classification and Retrieval are ONE , 2015, ICMR.

[5]  Shuicheng Yan,et al.  LG-CNN: From local parts to global discrimination for fine-grained recognition , 2017, Pattern Recognit..

[6]  Xiaogang Jin,et al.  Two-level hierarchical feature learning for image classification , 2016, Frontiers of Information Technology & Electronic Engineering.

[7]  Frank Hutter,et al.  SGDR: Stochastic Gradient Descent with Warm Restarts , 2016, ICLR.

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[9]  Dong Liu,et al.  Robust late fusion with rank minimization , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[11]  Andrew Zisserman,et al.  BiCoS: A Bi-level co-segmentation method for image classification , 2011, 2011 International Conference on Computer Vision.

[12]  Qi Tian,et al.  Good Practice in CNN Feature Transfer , 2016, ArXiv.

[13]  Rong Jin,et al.  Fine-grained visual categorization via multi-stage metric learning , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Yu Liu,et al.  On the Exploration of Convolutional Fusion Networks for Visual Recognition , 2016, MMM.

[15]  Edward M. Riseman,et al.  Indexing Flower Patent Images Using Domain Knowledge , 1999, IEEE Intell. Syst..

[16]  Luc Van Gool,et al.  TriCoS: A Tri-level Class-Discriminative Co-segmentation Method for Image Classification , 2012, ECCV.

[17]  David Zhang,et al.  Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification , 2014, International Journal of Computer Vision.

[18]  Qi Tian,et al.  Contextual Exemplar Classifier-Based Image Representation for Classification , 2017, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Zheru Chi,et al.  Data Management for Live Plant Identification , 2003 .

[20]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  David Masip,et al.  Winner takes all hashing for speeding up the training of neural networks in large class problems , 2017, Pattern Recognit. Lett..

[22]  Lin Wang,et al.  Metric forests based on Gaussian mixture model for visual image classification , 2018, Soft Comput..

[23]  Qi Tian,et al.  Hierarchical deep semantic representation for visual categorization , 2017, Neurocomputing.

[24]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[25]  Tzu-Hsiang Hsu,et al.  An interactive flower image recognition system , 2010, Multimedia Tools and Applications.

[26]  Andrew Zisserman,et al.  Delving into the Whorl of Flower Segmentation , 2007, BMVC.

[27]  Qi Tian,et al.  Image classification using Harr-like transformation of local features with coding residuals , 2013, Signal Process..

[28]  Qun Liu,et al.  CNN Features Off-the-Shelf : Clustering and Finetune-free , 2018 .

[29]  Andrew Zisserman,et al.  Automated Flower Classification over a Large Number of Classes , 2008, 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing.

[30]  Shuicheng Yan,et al.  Task-Driven Feature Pooling for Image Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[31]  P Kenrick Botany: The family tree flowers , 1999, Nature.

[32]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[33]  Rogério Schmidt Feris,et al.  Fusing well-crafted feature descriptors for efficient fine-grained classification , 2014, ICIP.

[34]  Qiang Chen,et al.  Hierarchical matching with side information for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[35]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[36]  Andrew Zisserman,et al.  Delving deeper into the whorl of flower segmentation , 2010, Image Vis. Comput..

[37]  Rong Xiao,et al.  Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern , 2014, IEEE Trans. Pattern Anal. Mach. Intell..

[38]  Haibin Ling,et al.  Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering , 2014, IEEE Transactions on Image Processing.

[39]  Xiu-Shen Wei,et al.  Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval , 2016, IEEE Transactions on Image Processing.

[40]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Yoshua Bengio,et al.  ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[42]  Naila Murray,et al.  Generalized Max Pooling , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[43]  Satoshi Ito,et al.  Object Classification Using Heterogeneous Co-occurrence Features , 2010, ECCV.

[44]  Jie Zou,et al.  Evaluation of model-based interactive flower recognition , 2004, ICPR 2004.

[45]  Tinne Tuytelaars,et al.  Mining Mid-level Features for Image Classification , 2014, International Journal of Computer Vision.

[46]  Aybars Ugur,et al.  Extraction of flower regions in color images using ant colony optimization , 2011, WCIT.

[47]  Pietro Perona,et al.  Visipedia circa 2015 , 2016, Pattern Recognit. Lett..

[48]  Qi Tian,et al.  Towards Reversal-Invariant Image Representation , 2017, International Journal of Computer Vision.

[49]  Qi Tian,et al.  Incorporating visual adjectives for image classification , 2016, Neurocomputing.

[50]  Fahad Shahbaz Khan,et al.  Modulating Shape Features by Color Attention for Object Recognition , 2012, International Journal of Computer Vision.

[51]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[52]  Jiro Katto,et al.  Deep Residual Learning for Image Compression , 2019, CVPR Workshops.

[53]  Umapada Pal,et al.  Collaborative representation based fine-grained species recognition , 2016, 2016 International Conference on Image and Vision Computing New Zealand (IVCNZ).

[54]  Andrew Zisserman,et al.  A Visual Vocabulary for Flower Classification , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).