Title: Identification of Damaged Wheat Kernels and Cracked-Shell Hazelnuts with Impact Acoustics Time-Frequency Patterns Authors
|Ince, Firat -|
|Onaran, Ibrahim -|
|Tewfik, Ahmed -|
|Cetin, A. Enis -|
|Kalkan, Habil -|
|Yardimci, Yasemin -|
Submitted to: Transactions of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: August 1, 2008
Publication Date: September 1, 2008
Repository URL: http://naldc.nal.usda.gov/download/23087/PDF
Citation: Ince, F., Onaran, I., Pearson, T.C., Tewfik, A., Cetin, A., Kalkan, H., Yardimci, Y. 2008. Identification of Damaged Wheat Kernels and Cracked-Shell Hazelnuts with Impact Acoustics Time-Frequency Patterns. Transactions of the ASABE. 51(4):1461-1469. Interpretive Summary: A new method for identifying and separating damaged wheat kernels and cracked-shell hazelnuts was developed. The method uses the sound emanating as wheat or nuts drop onto a plate as the basis for discrimination. The new approach separated insect and fungal damaged wheat kernels from undamaged wheat kernels with 96% and 94% accuracy, respectively. It also separated cracked-shell hazelnuts from those with undamaged shells with 97.1% accuracy. The method is highly adaptable and should find uses for other food kernel inspections as well.
Technical Abstract: A new adaptive time-frequency (t-f) analysis and classification procedure is applied to impact acoustic signals for detecting hazelnuts with cracked shells and three types of damaged wheat kernels. Kernels were dropped onto a steel plate, and the resulting impact acoustic signals were recorded with a PC-based data acquisition system. These signals were segmented with a flexible local discriminant bases (F-LDB) procedure in the time-frequency plane to extract discriminative patterns between damaged and undamaged food kernels. The F-LDB procedure requires no prior knowledge of the relevant time or frequency indices of the impact acoustics signals for classification. The method automatically finds all crucial time-frequency indices from the training data by combining local cosine packet analysis and a frequency axis clustering approach, which supports individual time and frequency band adaptation. Discriminant features are extracted from the adaptively segmented acoustic signal, sorted according to a Fisher class separability criterion, post-processed by principal component analysis, and fed to a linear discriminant classifier. Experimental results establish the superior performance of the proposed approach when compared to prior techniques reported in the literature or used in the field. The new approach separated damaged wheat kernels (IDK, pupal, and scab) from undamaged wheat kernels with 96%, 82%, and 94% accuracy, respectively. It also separated cracked-shell hazelnuts from those with undamaged shells with 97.1% accuracy. The adaptation capability of the algorithm to the time-frequency patterns of signals makes it a universal method for food kernel inspection that can resist the impact acoustic variability between different kernel and damage types.