Egg weight prediction and egg size classification using image processing and machine learning

Thipakorn, Jeerapa; Waranusast, Rattapoom; Riyamongkol, Panomkhawn

doi:10.1109/ecticon.2017.8096278

Cited by 23 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We also showed that TCAD data can be generated accurately and at low-cost (150,000 simulations in 2 weeks on 1 server), and studied the minimum amount of TCAD data that are required to train an accurate ML model for the analysis of experimental data. This framework allows the use of various types of ML algorithms, from the simplest linear regression to more sophisticated neural network [8] [9]. Principal Component Analysis (PCA) followed by third order polynomial regression is used in this paper.…”

mentioning

confidence: 99%

TCAD-Machine Learning Framework for Device Variation and Operating Temperature Analysis With Experimental Demonstration

Wong

Xiao

Wang

et al. 2020

IEEE J. Electron Devices Soc.

View full text Add to dashboard Cite

This work, for the first time, experimentally demonstrates a TCAD-Machine Learning (TCAD-ML) framework to assist the analysis of device-to-device variation and operating (ambient) temperature without the need of physical quantities extraction. The ML algorithm used in this work is the Principal Component Analysis (PCA) followed by third order polynomial regression. After calibrated to limited 'expensive' experimental data, 'low cost' TCAD simulation is used to generate a large amount of device data to train the ML model. The ML was then used to identify the root cause of device variation and operating temperature from any given experimental current-voltage (I-V) characteristics. We applied this framework to study the ultra-wide-bandgap gallium oxide (Ga2O3) Schottky barrier diode (SBD), an emerging device technology that holds great promise for temperature sensing, RF, and power applications in harsh environments. After calibration, over 150,000 electrothermal TCAD simulations are performed with random variation of physical parameters (anode effective work function, drift layer doping, and drift layer thickness) and operating temperature. An ML model is trained using these TCAD data and we found 1,000-10,000 TCAD data can train an accurate machine. We show that without physical quantities extraction, performing PCA is essential for the TCAD trained ML model to be applicable to analyze experimental characteristics. The physical parameters and temperatures predicted by the ML model show good agreement with experimental analysis. Our TCAD-ML framework shows great promise to accelerate the development of new device technologies with a significantly more efficient process of material and device experimentation.

show abstract

mentioning

confidence: 99%

TCAD-Machine Learning Framework for Device Variation and Operating Temperature Analysis With Experimental Demonstration

Wong

Xiao

Wang

et al. 2020

IEEE J. Electron Devices Soc.

View full text Add to dashboard Cite

show abstract

“…Most of the studies in the literature have been carried out on still images for detecting and determining the size and weight of eggs [ 16 , 47 , 48 , 49 ]. In these studies, measurements were made by fixing the egg on the floor to be imaged and the success rates were obtained as 87.6% by Thipakorn et al [ 49 ], and 95.0% by Cen et al [ 16 ]. However, in industrial egg production facilities for bulk production, it is required to measure egg parameters in real-time.…”

Section: Resultsmentioning

confidence: 99%

“…In the literature, there are limited studies on determining the volume and weight of chicken eggs. Many studies have been performed by image processing of the egg in a still position under a single light source [ 16 , 47 , 48 , 49 ]. However, in batch processing single flow lines and still image-based approaches are not of concern.…”

Section: Related Studiesmentioning

confidence: 99%

A Multi-Flow Production Line for Sorting of Eggs Using Image Processing

Akkoyun

Özçelik

Arpacı

et al. 2022

Sensors

View full text Add to dashboard Cite

In egg production facilities, the classification of eggs is carried out either manually or by using sophisticated systems such as load cells. However, there is a need for the classification of eggs to be carried out with faster and cheaper methods. In the agri-food industry, the use of image processing technology is continuously increasing due to the data processing speed and cost-effective solutions. In this study, an image processing approach was used to classify chicken eggs on an industrial roller conveyor line in real-time. A color camera was used to acquire images in an illumination cabinet on a motorized roller conveyor while eggs are moving on the movement halls. The system successfully operated for the grading of eggs in the industrial multi-flow production line in real-time. There were significant correlations among measured weights of the eggs after image processing. The coefficient of linear correlation (R2) between measured and actual weights was 0.95.

show abstract

“…Using detecting algorithms, several fruit characters are retrieved from the side view of the fruit image. In addition, image processing methods were presented by Thipakorn et al [13] and Wranusast et al [14] for estimating chicken egg weight and categorizing egg size number from a single egg image. With the use of MATLAB programming and the fuzzy logic toolbox, it is also possible to determine the egg fertility by implementing Image Processing and FLC in MATLAB [15].…”

Section: Related Workmentioning

confidence: 99%

Fuzzy Logic-Based Size and Ripeness Classification of Banana using Image Processing Technique

Malabag¹,

Santiago²,

Cahapin³

et al. 2022

IJETAE

View full text Add to dashboard Cite

The grading of banana ripeness and size are currently done manually by farmers and vendors following a certain process. It will assist producers grade the fruit, sellers set the best price, and customers get the most for their money if a system to automatically categorize bananas is proposed and developed. In this study, the size and maturity of bananas were classified using image processing and fuzzy logic techniques in MATLAB. This paper is segmented into five stages which are the image pre-processing, image processing, determination of length and thickness, size classification and ripeness classification. The metrics of length and thickness were used to classify banana sizes, while methods of image processing such as color segmentation and calculating the intensity of mean color based on RGB were used to classify banana ripeness. The classification of the banana was done using fuzzy logic in the decision-making process. Keywords—banana classification, fuzzy logic, image processing, defuzzification, banana grading

show abstract

Egg weight prediction and egg size classification using image processing and machine learning

Cited by 23 publications

References 2 publications

TCAD-Machine Learning Framework for Device Variation and Operating Temperature Analysis With Experimental Demonstration

TCAD-Machine Learning Framework for Device Variation and Operating Temperature Analysis With Experimental Demonstration

A Multi-Flow Production Line for Sorting of Eggs Using Image Processing

Fuzzy Logic-Based Size and Ripeness Classification of Banana using Image Processing Technique

Contact Info

Product

Resources

About