Flower classification using deep convolutional neural networks

Hiary, Hazem; Saadeh, Heba; Saadeh, Maha; Yaqub, Mohammad

doi:10.1049/iet-cvi.2017.0155

Cited by 70 publications

(38 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The segmentation process can be also involved for computer vision model based on deep learning. For example, (Hiary, Saadeh, Saadeh, & Yaqub, 2018) developed deep learning-based method to segment and classify flower images. Fully Convolutional Network (FCN) framework method was developed for segmenting the flower region that localises the flower by detecting the minimum bounding box around the object.…”

Section: Related Workmentioning

confidence: 99%

“…CNN has recently gained a lot of interest in solving numerous learning problems due to greater accuracy compared with classical methods. Hiary et al, developed a CNN method to accurately classify the different flower classes (Hiary, Saadeh, Saadeh, & Yaqub, 2018). In another work, CNN model has been proposed for implementing flower classification directly from flower images on Oxford 102 and KL University Flower Dataset (KLUFD) of 30 classes (designed for the study) sum out of 9500 flower images with 132 classes in (Prasad, et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Image Dataset Construction for Flower Recognition Using Convolutional Neural Network

Omer

Hasan

Anwer

2020

SJUOZ

View full text Add to dashboard Cite

Classifying flowers is a difficult activity because of the wide variety of flower species that have similar form. In this paper, a deep learning model for extracting features and classifying different flower types or species developed by using a popular method called Convolutional Neural Network (CNN). The identification system has been evaluated on a new dataset that has been designed in this work that collected flowers from Kurdistan. The dataset contains 1300 images of different flowers, 1040 images (%80) of which used for training purpose and 260 (%20) images used for test purpose, categorized into 26 classes. In addition, Various number of layers, activation function and pooling schemes were implemented to improve the classification rates. The recognition rate of proposed CNN model is 94.61%.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

An Image Dataset Construction for Flower Recognition Using Convolutional Neural Network

Omer

Hasan

Anwer

2020

SJUOZ

View full text Add to dashboard Cite

show abstract

“…The study is [27] used CNN in mango classification and achieved an accuracy of 99%. The authors in [28] classified flowers using CNN with an accuracy of 97%. Even though many of the relevant work that applied CNN used big datasets, there are some researches that achieved good results using small datasets.…”

Section: • K-nearest Neighbormentioning

confidence: 99%

Date Grading using Machine Learning Techniques on a Novel Dataset

Raissouli¹,

Aljabri²,

Aljudaibi³

et al. 2020

IJACSA

View full text Add to dashboard Cite

Dates grading is a crucial stage in the dates' factories. However, it is done manually in most of the Middle Eastern industries. This study, using a novel dataset, identifies the suitable machine learning techniques to grade dates based on the image of the date. The dataset consists of three different types of dates, namely, Ajwah, Mabroom, and Sukkary with each having three different grades. The dates were obtained from Manafez company and graded by their experts. The color, size and texture of the dates are the features that have been considered in this work. To determine the color, we have used color properties in RGB (red, green, and blue) color space. For measuring the size, we applied the best least-square fitting ellipse. To analyze the texture, we used Weber local descriptor to distinguish between texture patterns. In order to identify the suitable grading classifier, we have experimented three approaches, namely, k-nearest neighbor (KNN), support vector machine (SVM) and convolutional neural network (CNN). Our experiments have shown that CNN is the best classifier with an accuracy of 98% for Ajwah, 99% for Mabroom, and 99% for Sukkary. Hence, the CNN classifier has been incorporated in our date grading system.

show abstract

“…One of the existing systems for classification of flowers is using Random Forest Classifier method [11], reporting an average accuracy of 80.67% for a database of 10 different flowers. A more superior system [12] has used CNN and acquired an accuracy above 97%. It was done in two steps viz.…”

Section: Literature Review a Existing Systemsmentioning

confidence: 99%

Analysis of Pre-Trained Convolutional Neural Networks to Build a Flower Classification System

Gadkari¹

2019

IJRASET

View full text Add to dashboard Cite

Nature Tourism is an industry that is currently thriving and a lot of tourists visit places abundant in flora and fauna. A lot of times while hiking, tourists come across exotic looking flowers that mesmerize them but they are unable to discern what species the flowers belong to. The system proposed in this paper can help nature enthusiasts identify these flowers correctly. The proposed system examines the various features of the flower and identifies it by retraining models on flower datasets, using transfer learning methods. A review of three convolutional neural network models pre-trained on the ImageNet dataset, using the TensorFlow backend, was conducted to suggest the superior algorithm for flower classification systems in order to identify plant species accurately. The system was then implemented in the form of an Android mobile application that provides relevant information along with the species and family of the flower.

show abstract

Flower classification using deep convolutional neural networks

Cited by 70 publications

References 58 publications

An Image Dataset Construction for Flower Recognition Using Convolutional Neural Network

An Image Dataset Construction for Flower Recognition Using Convolutional Neural Network

Date Grading using Machine Learning Techniques on a Novel Dataset

Analysis of Pre-Trained Convolutional Neural Networks to Build a Flower Classification System

Contact Info

Product

Resources

About