Abstract
Leaf venation extraction studies have been strongly discouraged by considerable challenges posed by venation architectures that are complex, diverse and subtle. Additionally, unpredictable local leaf curvatures, undesirable ambient illuminations, and abnormal conditions of leaves may coexist with other complications. While leaf venation extraction has high potential for assisting with plant phenotyping, speciation and modelling, its investigations to date have been confined to colour image acquisition and processing which are commonly confounded by the aforementioned biotic and abiotic variations. To bridge the gaps in this area, we have designed a 3D imaging system for leaf venation extraction, which can overcome dark or bright ambient illumination and can allow for 3D data reconstruction in high resolution. We further propose a novel leaf venation extraction algorithm that can obtain illumination-independent surface normal features by performing Photometric Stereo reconstruction as well as local shape measures by fusing the decoupled shape index and curvedness features. In addition, this algorithm can determine venation polarity – whether veins are raised above or recessed into a leaf. Tests on both sides of different leaf species with varied venation architectures show that the proposed method is accurate in extracting the primary, secondary and even tertiary veins. It also proves to be robust against leaf diseases which can cause dramatic changes in colour. The effectiveness of this algorithm in determining venation polarity is verified by it correctly recognising raised or recessed veins in nine different experiments.
Highlights
Leaf venation is the patterned veins in the blade of a leaf
We propose a Photometric Stereo (PS) based 3D imaging system together with a compatible and novel algorithm for accurate and robust leaf venation extraction
Our research aims at resolving challenges and bridging gaps in this area, which leads to a synergistic investigation of 3D image system and data acquisition, modelling of leaf venation, and robust and salient feature extraction
Summary
Leaf venation is the patterned veins in the blade of a leaf. Leaf veins are considered to be related to resource delivery rates and photosynthetic capacity, but their high potential is undervalued and studies are limited [1]. This branch of computer vision studies is still at its youth, a few studies have shown that leaf venation extraction can greatly benefit plant speciation [4], phenotyping [5], as well as measuring physiological properties of plants (e.g. water transport and flow velocity in leaves [6]) It can even be of evolutionary significance by being able to reveal gene induced traits [7,8]. Apart from inherent variations that pose great challenges to leaf venation extraction, environmental factors further magnify this by causing complications such as leaf dehydration, powdery mildew, leaf curl, leaf mottling, etc Investigations of these different traits [9] in laboratory environments often enforce sufficient and homogeneous lighting to avoid presence of severe shadows and specularities. 3) The proposed method can overcome undesirable variations commonly found in real-world environments such as illumination changes and abnormalities induced by leaf diseases
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
