كلاس‌بندي پسته با استفاده از تكنيك‌هاي پردازش تصوير و شبكه نروفازي تطبيق‌پذير

Sorting of pistachio nuts using image processing techniques and an adaptive neural-fuzzy inference system

پسته از نظر شكاف پوست به دو دسته خندان (درباز) و ناخندان (دربسته) و از نظر مغز به دو دسته مغزدار و پوك تقسیم می‌شود. پسته‌های پوك و دربسته غالباً جزء محصول درخت پسته بوده و به دلیل ارزش كمتر نسبت به نوع مغزدار درباز باید دسته‌بندی شوند. هدف این پژوهش ارائه روشی هوشمند برای مرتب‌سازی پسته‌های دربسته، درباز مغزدار و پوك می‌باشد. داده‌های مورد نیاز برای دسته‌بندی با استفاده از تصاویر تهیه شده از نمونه‌های دربسته، مغزدار و پوك پسته با شرایط یكسان، تأمین شده است. به این ترتیب كه ابتدا برای استخراج تصویر پسته از پس زمینه آن، تصاویر تهیه شده به كمك تكنیك‌های پردازش تصویر، قطعه‌بندی شده و پس از انجام فیلترهایی بر روی تصاویر حاصل، برای تعیین با ارزش‌ترین ویژگی‌ها جهت دسته‌بندی، از الگوریتم یادگیری ماشین C4.5 و درخت تصمیم استفاده شد. ویژگی‌های ممان و اسكلت به‌عنوان با ارزش‌ترین ویژگی‌ها انتخاب شده و بر این اساس قوانین به‌دست آمده از درخت تصمیم به یك سیستم نرو-فازی تطبیق‌پذیر تغذیه شدند. این قوانین به‌صورت اگر-آنگاه بودند كه با پیمایش بالا به پایین حریص از ریشه تا برگ توسط الگوریتم C4.5 استخراج شده بودند. شبكه نروفازی ابتدا با استفاده از داده‌های استخراج شده مربوط به 200 نمونه شامل انواع دربسته، پوك و مغزدار و با دقت 8/95% آموزش داده شد. همچنین از 100 نمونه برای آزمایش سیستم با دقت97% استفاده شد.

Introduction: Pistachio nut is one of the most important agricultural products of Iran and it is priced due to the quality and type. One of the significant factors of pistachio cost is its type in terms of shell. Filled split pistachio nut has the most quality and is utilized as nuts, while the closed shell type has lower cost, at the same time is economically efficient in food industry such as confectionery. Now, pistachio sorting is performed usually by human and sometimes using electromechanical apparatuses. Classification of pistachio by human is time consuming and is done with an unacceptable accuracy, on the other hand, electromechanical and electro optical apparatuses damages pistachio because the mechanism used in them while separating. So, the need to develop automated systems that could be implemented by intelligent ways is evident to increase the speed and accuracy of classification. Materials and Methods: In this study, 300 samples of pistachios contains 100 Filled split, 100 Filled non-split and 100 split blank nuts ones are used. The training set consisted of 60 samples of each type of opened nuts, closed and empty opened shell nuts a total of 180 samples and the evaluation set consisted of 40 samples of each type of opened shell, closed shell and empty opened shell nuts a total of 120 samples. The principle of this study is implemented in two steps: 1) sample imaging and image processing to extract features 2) fuzzy network design based on the characteristics of data and training. To select useful features from the hypothesis, C4.5 decision tree is used. C4.5 algorithm makes a greedy top to bottom search on the hypothesis, and is made by the question what feature must be at the root of the tree. By the help of statistical methods, extracted features from the images were prioritized and the most appropriate features for classification of training set were selected. The algorithm chooses the best features as their number is minimum. Finally, a total amount of the second moment (m2) and matrix vectors of image were selected as features. Features and rules produced from decision tree fed into an Adaptable Neuro-fuzzy Inference System (ANFIS). ANFIS provides a neural network based on Fuzzy Inference System (FIS) can produce appropriate output corresponding input patterns. Results and Discussion: The proposed model was trained and tested inside ANFIS Editor of the MATLAB software. 300 images, including closed shell, pithy and empty pistachio were selected for training and testing. This network uses 200 data related to these two features and were trained over 200 courses, the accuracy of the result was 95.8%. 100 image have been used to test network over 40 courses with accuracy 97%. The time for the training and testing steps are 0.73 and 0.31 seconds, respectively, and the time to choose the features and rules was 2.1 seconds. Conclusions: In this study, a model was introduced to sort non- split nuts, blank nuts and filled nuts pistachios. Evaluation of training and testing, shows that the model has the ability to classify different types of nuts with high precision. In the previously proposed methods, merely non-split and split pistachio nuts were sorted and being filled or blank nuts is unrecognizable. Nevertheless, accuracy of the mentioned method is 95.56 percent. As well as, other method sorted non-split and split pistachio nuts with an accuracy of 98% and 85% respectively for training and testing steps. The model proposed in this study is better than the other methods and it is encouraging for the improvement and development of the model.