Pixelwise Complex-Valued Neural Network Based on 1D FFT of Hyperspectral Data to Improve Green Pepper Segmentation in Agriculture

It seems difficult to recognize an object from its background with similar color using conventional segmentation methods. An efficient way is to utilize hyperspectral images that contain more wave bands and richer information than only RGB components. Particularly in our task, we aim to separate a pepper from densely packed green leaves for automatic picking in agriculture. Given that hyperspectral imaging can be regarded as a kind of wave propagation process, we make a novel attempt of introducing a complex neural network tailored for wave-related problems. Due to the lack of hyperspectral data, pixelwise training is deployed, and 1D fast Fourier transform of the hyperspectral data is used for the construction of complex input. Experimental results have showcased that a complex neural network outperforms a real-valued one in terms of detection accuracy by 3.9% and F1 score by 1.33%. Moreover, it enables the ability to select frequency bands used such as low-frequency components to boost performance as well as prevent overfitting problems for learning more generalization features. Thus, we put forward a lightweight pixelwise complex model for hyperspectral-related problems and provide an efficient way for green pepper automatic picking in agriculture using small datasets.

[1]  Mohammed Q. Alkhatib,et al.  Complex-valued neural network for hyperspectral single image super resolution , 2023, Photonex.

[2]  T. Kurihara,et al.  Hyperspectral imaging for green pepper segmentation using a complex-valued neural network , 2022, Optik.

[3]  Ehsan Dehghan-Niri,et al.  Non-destructive thermal imaging for object detection via advanced deep learning for robotic inspection and harvesting of chili peppers , 2021 .

[4]  Jun Yu,et al.  Optical Filter Net: A Spectral-Aware RGB Camera Framework for Effective Green Pepper Segmentation , 2021, IEEE Access.

[5]  Chi-Man Pun,et al.  Endmember Extraction of Hyperspectral Remote Sensing Images Based on an Improved Discrete Artificial Bee Colony Algorithm and Genetic Algorithm , 2018, Mob. Networks Appl..

[6]  Cheng Shi,et al.  Superpixel-based 3D deep neural networks for hyperspectral image classification , 2018, Pattern Recognit..

[7]  Junichi Kurihara,et al.  A novel approach for vegetation classification using UAV-based hyperspectral imaging , 2018, Comput. Electron. Agric..

[8]  Yong He,et al.  Hyperspectral imaging for classification of healthy and gray mold diseased tomato leaves with different infection severities , 2017, Comput. Electron. Agric..

[9]  Les E. Atlas,et al.  Full-Capacity Unitary Recurrent Neural Networks , 2016, NIPS.

[10]  Peteris Eizentals,et al.  3D pose estimation of green pepper fruit for automated harvesting , 2016, Comput. Electron. Agric..

[11]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Fan Zhang,et al.  Deep Convolutional Neural Networks for Hyperspectral Image Classification , 2015, J. Sensors.

[13]  E. J. van Henten,et al.  Robust pixel-based classification of obstacles for robotic harvesting of sweet-pepper , 2013 .

[14]  Akira Hirose,et al.  Generalization Characteristics of Complex-Valued Feedforward Neural Networks in Relation to Signal Coherence , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[15]  Jacek M. Zurada,et al.  Blur Identification by Multilayer Neural Network Based on Multivalued Neurons , 2008, IEEE Transactions on Neural Networks.

[16]  Akira Hirose,et al.  Complex-Valued Neural Networks , 2006, Studies in Computational Intelligence.

[17]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Yuanliang Ma,et al.  CGHA for principal component extraction in the complex domain , 1997, IEEE Trans. Neural Networks.

[19]  Donald L. Birx,et al.  A complex mapping network for phase sensitive classification , 1993, IEEE Trans. Neural Networks.