Computer vision system and near-infrared spectroscopy for identification and classification of chicken with wooden breast, and physicochemical and technological characterization

Gerônimo, Bruna Caroline; Mastelini, Saulo Martiello; Carvalho, Rafael H.; Júnior, Sylvio Barbon; Barbin, Douglas Fernandes; Shimokomaki, Massami; Ida, Elza Iouko

doi:10.1016/j.infrared.2018.11.036

Cited by 57 publications

(42 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiang et al [35] selecting seven wavelengths, among them 581 and 631, obtained a 91.7% classification rate. These studies have measured the same cranial location of the breast as in our study that has been found to be the most discriminant area [33,35]. Nevertheless, the implementation of these other methods in the poultry industry is very limited at the moment due to their cost or complexity.…”

Section: Colormentioning

confidence: 78%

“…Other methods have been used to discriminate normal samples without myopathies. Computer Vision System in combination with near-infrared spectroscopy has been applied to the classification of WB [33]. A 96.3% cross-validation accuracy was obtained in detecting WB samples using six wavelengths from 1261 nm onwards, although they cannot be directly compared with visible spectra.…”

Section: Colormentioning

confidence: 99%

See 1 more Smart Citation

Differentiating Breast Myopathies through Color and Texture Analyses in Broiler

Mur

Guerrero

Barahona

et al. 2020

Foods

View full text Add to dashboard Cite

Wooden breast (WB), white striping (WS) and spaghetti meat (SM) are breast myopathies of the Pectoralis major that greatly affect meat quality in broilers. To differentiate color and texture characteristics with instrumental methods, some of them applied for the first time in this species, 300 carcasses were randomly chosen from an abattoir from five different flocks from the same farm, at a rate of 60 carcasses from each flock. Twenty-four hours after slaughter, both side breasts were dissected, and yields calculated. Color was measured on the surface of the breast with a spectrocolorimeter and reflectance values obtained. Texture was measured on raw meat with a modified compression test that hinders the fiber from expanding transversally and a texture profile analysis (TPA) and also on cooked meat with a Warner–Bratzler shear and a TPA. Color differs between severity degrees, increasing redness (from −1.77 to −1.32 in WB) and, especially, yellowness (from 5.00 to 6.73 in WS) and chroma (from 5.75 to 7.22 in SM) with the severity of the myopathy. The subtraction R630 minus R580 was found to be a useful index to differentiate breast myopathies degrees. The modified compression test can be considered an effective tool to assess the hardness of different structures in each myopathy. Texture differences in the myopathies are better assessed in raw than in cooked meat.

show abstract

Section: Colormentioning

confidence: 78%

Section: Colormentioning

confidence: 99%

Differentiating Breast Myopathies through Color and Texture Analyses in Broiler

Mur

Guerrero

Barahona

et al. 2020

Foods

View full text Add to dashboard Cite

show abstract

“…Computer vision has been widely used in various processes of different poultry production systems. It includes automation of the house management, behavior, and welfare [11,[29][30][31][32][33][34][35][36][37][38][39][40], disease detection [28,[41][42][43][44][45][46][47], weight measurement [27,[48][49], slaughtering process [50][51], carcass quality [52][53][54][55], and egg examination [56][57][58][59][60][61][62][63][64][65]. On the other hand, computer vision also popular on other livestock monitoring, such as pig [73][74][75][76][77][78][79][80], sheep or cattle …”

Section: Overview Of Computer Vision In Poultry Farmmentioning

confidence: 99%

“…In the poultry industry, the rapid development of computer vision is indistinguishable from the hardware aspect of computer vision. In general, a camera with a lens, a lighting unit, a motor-driven mobile station, and a computer packed with image acquisition and analysis software are traditional computer vision [53], as shown in Fig. 1.…”

Section: Hardwarementioning

confidence: 99%

A Review on Computer Vision Technology for Monitoring Poultry Farm—Application, Hardware, and Software

et al. 2021

View full text Add to dashboard Cite

“…In addition, NIR spectroscopy can be used in industrial processing lines for the classification/authentication of samples (Barbin, ElMasry, Sun, & Allen, 2013; Perez et al., 2018). Multivariate statistical analyses are necessary to extract useful information from NIR spectra, and thus, have been applied to distinguish the different samples or concentration of specific chemical compounds in chicken or turkey with WS or WB myopathies (Geronimo et al., 2019; Wold, Måge, Løvland, Sanden, & Ofstad, 2019; Wold, Veiseth‐Kent, Host, & Lovland, 2017; Zaid, Abu‐Kalaf, Mudalal, & Petracci, 2020).…”

Section: Introductionmentioning

confidence: 99%

Occurrence of wooden breast and white striping in Brazilian slaughtering plants and use of near‐infrared spectroscopy and multivariate analysis to identify affected chicken breasts

Carvalho

Madruga

Estévez

et al. 2020

Journal of Food Science

Self Cite

View full text Add to dashboard Cite

White Striping (WS) and Wooden Breast (WB) are emerging poultry myopathies that occur worldwide, affecting the quality of meat. The aim of this study was to evaluate the occurrence of N, WS, WB, and WS/WB (myopathies combined) in chicken breast from Brazilian commercial plant, comparing (1) inspection based on visual aspect and palpation of Pectoralis major muscle, and (2) identification of these myopathies by near-infrared Spectroscopy (NIRS). Chickens slaughtered at Brazilian commercial plant at four age ranges (4 to 5, 6 to 7, 8 to 9, and 65 weeks) were inspected. Spectral information was acquired using a portable NIR spectrometer, and classification models were performed using and Successive Projection Algorithm-Linear Discriminant Analysis (SPA-LDA) and Soft Independent Modeling of Class Analogy (SIMCA) to distinguish normal and affected muscles. Results showed that occurrence of myopathies was aggravated by age of slaughter, as chicken slaughtered at 4 to 5 and 65 weeks exhibited 13.6 and 95% of myopathies, respectively. Birds slaughtered at 65 weeks showed no occurrence of WB, isolated or combined with WS. It was not possible to differentiate the WB and WS/WB classes; therefore, those samples were grouped (WB+WS/WB). SPA-LDA model showed greater accuracy (92 to 93%) in identifying Normal (N), WS, and WB+WS/WB groups, compared to SIMCA (89 to 91%). It can be concluded that the level of occurrence of myopathies in meat is directly related to the age of slaughter. This study demonstrated that NIRS combined with SPA-LDA model could be used as a tool to detect myopathies in chicken breast. This technique has potential for application in industrial processing lines as an alternative to the traditional methods of identification.

show abstract

Computer vision system and near-infrared spectroscopy for identification and classification of chicken with wooden breast, and physicochemical and technological characterization

Cited by 57 publications

References 33 publications

Differentiating Breast Myopathies through Color and Texture Analyses in Broiler

Differentiating Breast Myopathies through Color and Texture Analyses in Broiler

A Review on Computer Vision Technology for Monitoring Poultry Farm—Application, Hardware, and Software

Occurrence of wooden breast and white striping in Brazilian slaughtering plants and use of near‐infrared spectroscopy and multivariate analysis to identify affected chicken breasts

Contact Info

Product

Resources

About