Support vector machine approach to real-time inspection of biscuits on moving conveyor belt

Nashat, S.; Abdullah, Azizi; Aramvith, Supavadee; Abdullah, Mohd Zaid

doi:10.1016/j.compag.2010.10.010

Cited by 53 publications

(33 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For visual inspection of muffins, Abdullah et al (2000) developed an automated system incorporating multivariate discriminant algorithms to statistically classify muffins based on surface colour. The biscuits on a moving conveyor belt can be classified in real time into one of four distinct groups: underbaked, moderately baked, overbaked, and substantially overbaked (Nashat et al 2011). According to the manufacturing procedures of pizza, computer vision has been applied for quality assurance of pizza base, sauce spread, and topping (Du and Sun 2008b ity inspection of cheese, which are determination of the shreddability (Apostolopoulos and Marshall 1994), recognition of cheese shred dimensions (Ni and Gunasekaran 1995), measurement of the meltability, browning, and oiling off properties of Cheddar and Mozzarella cheeses under different cooking conditions and sizes of sample (Wang and Sun 2002, 2004a, inspection of the distribution and amount of ingredients in pasteurized cheese (Jeliński et al 2007), and monitoring curd syneresis in a cheese vat (Everard et al 2007;Fagan et al 2008).…”

Section: Applicationsmentioning

confidence: 99%

Computer Vision

Du¹,

Cheng²

2014

Food Engineering Series

View full text Add to dashboard Cite

Section: Applicationsmentioning

confidence: 99%

Computer Vision

Du¹,

Cheng²

2014

Food Engineering Series

View full text Add to dashboard Cite

“…Many wavelength selection algorithms, such as the successive projection algorithm (SPA) (Araújo and others ), genetic algorithm (GA) (Jarvis and Goodacre ), competitive adaptive reweighted sampling (CARS) (Li and others ), first‐derivative and mean centering iteration algorithm (FMCIA) (Su and Sun ), regression coefficient (RC) (He and others ), and principal components analysis (PCA) (Shahin and Symons ) have been introduced over the last couple of decades. The effective multivariate calibration models, including partial least squares regression (PLSR), principal component regression (PCR), multiple linear regression (MLR), artificial neural networks (ANN), support vector machines (SVM), and least square support vector machine (LS‐SVM), together with selected feature wavelengths for multispectral imaging, can be used for the online and nondestructive monitoring of food quality (Nashat and others ; Shahin and Symons ; Lorente and others ; Pu and others ). In principle, a good multivariate model should have high accuracy values, or determination coefficients in calibration ( R 2 C ), cross‐validation ( R 2 CV ), and prediction ( R 2 P ), and low values of root mean square errors in calibration (RMSEC), cross‐validation (RMSECV), and prediction (RMSEP).…”

Section: Chemometric Analysismentioning

confidence: 99%

Multispectral Imaging for Plant Food Quality Analysis and Visualization

Sun

2018

Comp Rev Food Sci Food Safe

102

View full text Add to dashboard Cite

The multispectral imaging technique is considered a reformation of hyperspectral imaging. It can be employed to noninvasively and rapidly evaluate food quality. Even though several imaging or sensor‐based techniques have been conducted for the quality assessment of various food products, the rise of multispectral imaging has been more promising. This paper presents a comprehensive review of the use of the multispectral sensor in the quality assessment of plant foods (such as cereals, legumes, tubers, fruits, and vegetables). Different quality parameters (such as physicochemical and microbiological aspects) of plant‐based foods that were determined and visualized by the combination of modeling methods and feature wavelength selection approaches are summarized. Based on the literature, the most frequently used wavelength selection methods are the successive projection algorithm (SPA) and the regression coefficient (RC). The most effective models developed for analyzing plant food products are the partial least squares regression (PLSR), least square support vector machine (LS‐SVM), support vector machine (SVM), partial least squares discriminant analysis (PLSDA), and multiple linear regression (MLR). This article concludes with a discussion of challenges, potential uses, and future trends of this flourishing technique that is now also being applied to plant foods.

show abstract

“…Afterwards, when a device is in use, the current data can be arranged according to these classifiers. The conventional SVM is too computationally intensive to apply on a real-time calculation [23], [24]. However, the gesture recognition of this device should respond rapidly and run This work is licensed under a Creative Commons Attribution 3.0 License.…”

Section: Introductionmentioning

confidence: 99%

Wrist-Worn Gesture Sensing With Wearable Intelligence

2019

View full text Add to dashboard Cite

This paper presents an innovative wrist-worn device with machine learning capabilities and a wearable pressure sensor array. The device is used for monitoring different hand gestures by tracking tendon movements around the wrist. Thus, an array of PDMS-encapsulated capacitive pressure sensors is attached to the user to capture wrist movement. The sensors are embedded on a flexible substrate and their readout requires a reliable approach for measuring small changes in capacitance. This challenge was addressed by measuring the capacitance via the switched capacitor method. The values were processed using a programme on LabVIEW to visually reconstruct the gestures on a computer. In addition, to overcome limitations of tendo's uncertainty when the wristband is re-worn, or the user is changed, a calibration step based on the support vector machine (SVM) learning technique is implemented. Sequential minimal optimization algorithm is also applied in the system to generate SVM classifiers efficiently in real-time. The working principle and the performance of the SVM algorithms demonstrate through experiments. Three discriminated gestures have been clearly separated by SVM hyperplane and correctly classified with high accuracy (>90%) during real-time gesture recognition.Index Terms-Support vector machine, sequential minimal optimization, gesture recognition, wearable intelligence, capacitance measurement.

show abstract

Support vector machine approach to real-time inspection of biscuits on moving conveyor belt

Cited by 53 publications

References 15 publications

Computer Vision

Computer Vision

Multispectral Imaging for Plant Food Quality Analysis and Visualization

Wrist-Worn Gesture Sensing With Wearable Intelligence

Contact Info

Product

Resources

About