Digital Microscopic Image Sensing and Processing for Leather Species Identification

Varghese, Anjli; Jain, Sahil; Prince, A. Amalin; Jawahar, Malathy

doi:10.1109/jsen.2020.2991881

Cited by 21 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Laser technology can be used to modify the surface of processed leather, providing a new way to tailor the material for different applications. [ 12 ]. Laser diode arrays (LDAs) increase the power of laser sources to multiple kilowatts while keeping brightness intact, thus broadening the range of applications for this technology [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Input Power of Diode Laser on Machined Leather Specimen in Laser Beam Cutting Process

et al. 2023

View full text Add to dashboard Cite

Numerous industries, including footwear, handicrafts, and the automobile industry, utilize leather materials. The main goal of this study was to investigate the effect of input power of the diode laser in laser cutting on vegetable chrome tanned buffalo leather to enhance the cutting process. In the present investigation, carbonization, kerf width, and material removal rate (MRR) were taken as performance measures. The diode-based laser beam machining was designed and fabricated with 2.5 W, 5.5 W, and 20 W diode laser to cut vegetable chrome tanned leather. The high-intensity 20 W diode laser produced lower carbonization, lower kerf width, and higher material removal rate compared with the 2.5 W and 5.5 W diodes. This improved performance was due to the adjustable features associated with this diode laser actuation in the form of circular shape with adjustable diameter. A high power with a lower spot size under pulsed mode can produce higher power density. Since a higher power density can establish less interaction time, it produces lower carbonization. Due to the ability of the 20 W diode laser driver to control the beam shape and size, it could produce a lower kerf width and higher MRR. The optimal parameters for cutting chrome vegetable tanned cow leather were a standoff distance of 18 mm, feed rate of 200 mm/min, and duty cycle of 70%.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Input Power of Diode Laser on Machined Leather Specimen in Laser Beam Cutting Process

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The classic species identification techniques involve human expert investigation, an expensive, tedious, and time-consuming approach. Such a manual process also often leads to uncertain and ambiguous decisionmaking [1]. On the other hand, image processing (IP) and machine learning (ML) methods on leather images can bring up an automated technique with consistent and quick decision-making.…”

Section: Introductionmentioning

confidence: 99%

“…The leather images are the ones that capture the discriminative hair-pore behavior of each species. In the recent works [1,2], the features of such species-specific pore patterns are extracted using the IP methods for automatic classification. Although, IP-based feature extraction is inappropriate for developing a fully-automated technique.…”

Section: Introductionmentioning

confidence: 99%

Fine-tuning ConvNets with novel leather image data for species identification

Varghese¹,

Jawahar

Prince³

2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

This paper introduces deep learning (DL) for leather species identification. It exploits the application of transfer learning on the existing Convolutional Neural Networks (ConvNets). The application of transfer learning fine-tunes the ConvNet parameters to learn the novel leather image data. This research investigates the performance of four ConvNets, namely, AlexNet, VGG16, GoogLeNet, and ResNet18, to predict the leather species. The comparative study affirms the efficacy of ResNet18 in learning the complex pore structural behavior of leather images. It efficiently classifies the leather images into four respective species with the highest accuracy (99.69%). It outperforms the existing ML-based prediction with a 7% improvement. Therefore, ConvNet is the best solution to deal with inter-species similarity and intra-species variability, the practical challenges of the leather images. It thus develops a fully-automated leather species identification technique that paves the way for biodiversity preservation and consumer protection.

show abstract

“…As a result it was observed that the buffalo skin had minute wavy pores [3]. In view of this, a scanning electron microscope (SEM)-based visual analysis of leather was developed [4]. The objective of this research is to analyze and quantify the process of cutting [5] a leather specimen.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Carbon Formation on Machined Leather Specimen Using FTIR Technique in Laser Diode Assisted Cutting Process

et al. 2022

View full text Add to dashboard Cite

The leather materials are used in a multitude of sectors, including footwear, apparel, handicrafts, and the automotive industry. Due to the radiant heat generated by a laser beam, the laser cutting of leather results in a carbonized cut edge. There is currently no technology available for measuring the carbonization along the contour edges of leather. The purpose of this experimental investigation was to determine the impact of power diode-based laser cutting on the carbonization of machined buffalo leather with the help of a digital microscope to improve the machining process. The ATR-FTIR spectrum was used to analyze the carbon-related functional group in the mid-IR spectrum of carbonized leather samples. It was found that the proposed method can measure the amount of carbon deposition in the cutting zone. The lower amplitude duty cycle with higher feed rate can reduce carbon formation owing to the lower thermal energy distribution. The amplitude (4.5 V), duty cycle (70%) and feed rate (90 mm/s) can produce optimal performance measures.

show abstract

Digital Microscopic Image Sensing and Processing for Leather Species Identification

Cited by 21 publications

References 23 publications

Performance Evaluation of Input Power of Diode Laser on Machined Leather Specimen in Laser Beam Cutting Process

Performance Evaluation of Input Power of Diode Laser on Machined Leather Specimen in Laser Beam Cutting Process

Fine-tuning ConvNets with novel leather image data for species identification

Analysis of Carbon Formation on Machined Leather Specimen Using FTIR Technique in Laser Diode Assisted Cutting Process

Contact Info

Product

Resources

About