LignoIndo: image database of Indonesian commercial timber

Abstract

Macroscopic image database of Indonesian commercial timber “LignoIndo” has been developed to support the development of a computer vision-based wood identification system. A total of 809 wood species were taken their macroscopic images by using digital loupe at two magnifications: 50 times and 200 times. All of these timber species are Indonesian commercial timber listed in LIU (License Information Unit) in November 2016. Cross section images of 186 wood species listed in the Ministry of Forestry Degree No 163/2003 were also collected by using mobile phone camera that was attached with 60x magnify lens, as the basis data to the mobile application of automatic wood identification tool (AIKO). The number of wood species in this database will continue to grow as the number of commercial wood species increases. Besides, the number of replicates of specimens for each species of wood can also continue to be added to accommodate wood variations in the same species, the same species from different trees, and different geographic locations. This paper presents data collection methods and summaries of wood data that have been collected including trade name, botanical name, family, durability classes, strength classes, commercial class classification, conservation status, and recommended utilization.

Computer vision-based wood identification and its expansion and contribution potentials in wood science: A review

“…CAIRO and FRIM, which contain stereogram images of commercial hardwood species in Malaysia, were among the first to be constructed and are still regularly updated [27,82]. LignoIndo, which also contains stereogram images, was constructed for the development of a portable wood identification system [83]. It contains images of Indonesian commercial hardwood species.…”

“…Recently, smartphone-based systems have been developed that require minimal components. MyWood-ID can identify 100 Malaysian woods [49], and another smartphone-based system, AIKO, can identify major Indonesian commercial woods [83]. XyloPhone, a smartphone-based imaging platform, has been introduced as a field-use identification tool that is more affordable and scalable than other commercial products [57].…”

“…XyloPhone, a smartphone-based imaging platform, has been introduced as a field-use identification tool that is more affordable and scalable than other commercial products [57]. All the field-deployable systems are based on stereogram datasets [21,49,51,57,69,83].…”

FTIDB: a new flue-cured tobacco leaf image database

“…Additionally, the database included hyperspectral images and computed tomography images of wood discs sampled from the ends of the logs 4 . Damayanti et al developed the "LignoIndo" database, an Indonesian commercial wood macro-image database, specifically designed to support the development of wood identification systems based on computer vision techniques 5 . Davinder Singh et al constructed a visual plant disease detection database containing 2598 data for 13 plant species and encompassing 17 disease categories.…”

Towards Sustainable North American Wood Product Value Chains, Part I: Computer Vision Identification of Diffuse Porous Hardwoods

“…To overcome the dearth of human expertise in wood identification, various teams have developed computer visionbased systems which can be implemented in the laboratory or in the field (Khalid et al, 2008;Martins et al, 2013;Filho et al, 2014;Figueroa-Mata et al, 2018;Ravindran et al, 2018Ravindran et al, , 2019Ravindran et al, , 2021Damayanti et al, 2019;de Andrade et al, 2020;Souza et al, 2020). Even with microscopic inspection and complete access to reference collections, humanbased wood identification is typically accurate only to the genus level with reliable species-level identification being rare (Gasson, 2011).…”