On the Efficacy of Handcrafted and Deep Features for Seed Image Classification

Computer vision techniques have become important in agriculture and plant sciences due to their wide variety of applications. In particular, the analysis of seeds can provide meaningful information on their evolution, the history of agriculture, the domestication of plants, and knowledge of diets in ancient times. This work aims to propose an exhaustive comparison of several different types of features in the context of multiclass seed classification, leveraging two public plant seeds data sets to classify their families or species. In detail, we studied possible optimisations of five traditional machine learning classifiers trained with seven different categories of handcrafted features. We also fine-tuned several well-known convolutional neural networks (CNNs) and the recently proposed SeedNet to determine whether and to what extent using their deep features may be advantageous over handcrafted features. The experimental results demonstrated that CNN features are appropriate to the task and representative of the multiclass scenario. In particular, SeedNet achieved a mean F-measure of 96%, at least. Nevertheless, several cases showed satisfactory performance from the handcrafted features to be considered a valid alternative. In detail, we found that the Ensemble strategy combined with all the handcrafted features can achieve 90.93% of mean F-measure, at least, with a considerably lower amount of times. We consider the obtained results an excellent preliminary step towards realising an automatic seeds recognition and classification framework.

[1]  Cecilia Di Ruberto,et al.  Detection of red and white blood cells from microscopic blood images using a region proposal approach , 2019, Comput. Biol. Medicine.

[2]  Darko Stefanovic,et al.  Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification , 2016, Comput. Intell. Neurosci..

[3]  Niko Sünderhauf,et al.  Evaluation of Features for Leaf Classification in Challenging Conditions , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[4]  Priyanka Dahiya,et al.  COMPARISONS OF CLASSIFICATION ALGORITHMS ON SEEDS DATASET USING MACHINE LEARNING ALGORITHM , 2018 .

[5]  Giorgio Giacinto,et al.  Convolutional neural networks for relevance feedback in content based image retrieval , 2020, Multimedia Tools and Applications.

[6]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[7]  Cecilia Di Ruberto,et al.  An Open Source Plugin for Image Analysis in Biology , 2019, 2019 IEEE 28th International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE).

[8]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Cecilia Di Ruberto,et al.  A novel deep learning based approach for seed image classification and retrieval , 2021, Comput. Electron. Agric..

[10]  Cecilia Di Ruberto,et al.  A Mobile Application for Leaf Detection in Complex Background Using Saliency Maps , 2016, ACIVS.

[11]  Andreas Kamilaris,et al.  Deep learning in agriculture: A survey , 2018, Comput. Electron. Agric..

[12]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Ali Amer Alwan,et al.  A Convolution Neural Network-Based Seed Classification System , 2020, Symmetry.

[14]  O. Grillo,et al.  Earliest evidence of a primitive cultivar of Vitis vinifera L. during the Bronze Age in Sardinia (Italy) , 2015, Vegetation History and Archaeobotany.

[15]  Gianluigi Bacchetta,et al.  Phenotypic identification of plum varieties (Prunus domestica L.) by endocarps morpho-colorimetric and textural descriptors , 2017, Comput. Electron. Agric..

[16]  Jaromir Przybylo,et al.  Using Deep Convolutional Neural Network for oak acorn viability recognition based on color images of their sections , 2019, Comput. Electron. Agric..

[17]  Rob Lind.  Open source software for image processing and analysis: picture this with ImageJ , 2012 .

[18]  Saira Gillani,et al.  Transfer learning-assisted multi-resolution breast cancer histopathological images classification , 2021, The Visual Computer.

[19]  Luigi Cinque,et al.  Decomposition of two-dimensional shapes for efficient retrieval , 2009, Image Vis. Comput..

[20]  Cecilia Di Ruberto,et al.  A fast leaf recognition algorithm based on SVM classifier and high dimensional feature vector , 2014, 2014 International Conference on Computer Vision Theory and Applications (VISAPP).

[21]  Cecilia Di Ruberto,et al.  An effective and friendly tool for seed image analysis , 2021, The Visual Computer.

[22]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[23]  Nagendra Gajjar,et al.  Real-time detection and identification of plant leaf diseases using convolutional neural networks on an embedded platform , 2021, The Visual Computer.

[24]  M. Dahari,et al.  Automatic detection of oil palm fruits from UAV images using an improved YOLO model , 2021, The Visual Computer.

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

[26]  Roberto Alejo,et al.  Assessments Metrics for Multi-class Imbalance Learning: A Preliminary Study , 2013, MCPR.

[27]  Marcel Salathé,et al.  Using Deep Learning for Image-Based Plant Disease Detection , 2016, Front. Plant Sci..

[28]  O. Grillo,et al.  Morpho-colorimetric characterisation of Malva alliance taxa by seed image analysis. , 2017, Plant biology.

[29]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

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

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

[32]  O. Grillo,et al.  Predictive Method for Correct Identification of Archaeological Charred Grape Seeds: Support for Advances in Knowledge of Grape Domestication Process , 2016, PloS one.

[33]  Cecilia Di Ruberto,et al.  Comparison of Statistical Features for Medical Colour Image Classification , 2015, ICVS.

[34]  O. Grillo,et al.  Inter- and intraspecific diversity in Cistus L. (Cistaceae) seeds, analysed with computer vision techniques. , 2017, Plant biology.

[35]  Alsayed Algergawy,et al.  A Deep Learning-based Approach for Banana Leaf Diseases Classification , 2017, BTW.

[36]  Utpal Barman,et al.  Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf disease , 2020, Comput. Electron. Agric..

[37]  Lianhe Yang,et al.  Recognition of carrot appearance quality based on deep feature and support vector machine , 2021, Comput. Electron. Agric..

[38]  A V Vlasov,et al.  A machine learning approach for grain crop’s seed classification in purifying separation , 2017 .

[39]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[40]  G. D’hallewin,et al.  First finds of Prunus domestica L. in Italy from the Phoenician and Punic periods (6th–2nd centuries bc) , 2017, Vegetation History and Archaeobotany.