Recognition of Slab Identification Numbers using a Fully Convolutional Network

Abstract

In the steel industry, slabs are manufactured with different amounts of alloying elements according to production purposes or final products. Because slabs have similar shapes, product identification is required to prevent inadequate production processes. In many steel mills, paint marking systems are widely used to inscribe slab identification numbers (SINs). As smart factory technology receives more attention in recent years, automatic recognition of SINs becomes more important for factory automation. The recognition of SINs is a challenging problem due to complex background of factory scenes and low quality of characters in SINs. To address this difficulties, this paper proposes a deep learning algorithm for recognizing SINs in factory scenes. Most existing recognition algorithms conduct text detection and classification using separate modules, and errors in each step are accumulated. The proposed algorithm employs a fully convolutional network (FCN) with deconvolution layers to integrate the recognition processes and improve the performance in processing time and accuracy. The main contribution of this work is on a novel type of ground-truth data (GTD) for the training of a FCN to recognize SINs in factory scenes. The relation between an input image and the corresponding GTD is directly trained in the manner of image-to-image training, and the FCN generates a prediction map that contains categorical information of individual pixels in an input image. Experiments were thoroughly conducted on industrial data collected from a steelworks to demonstrate the effectiveness of the proposed algorithm.

Selective Distillation of Weakly Annotated GTD for Vision-Based Slab Identification System

“…The previous algorithms for recognizing machine-printed SINs proposed in [30] and [53] are not applicable to the recognition of handwritten SINs because these methods used features of machine-printed characters such as consistent aspect ratio and similar distances between characters. However, characters in a handwritten SIN have irregular aspect ratios and varying distances between characters.…”

“…The identical datasets in [30] and [53] were used for the training and evaluation of the proposed algorithm. In summary, 1850 scenes with 3749 slabs, 543 scenes with 1102 slabs and 2108 scenes with 4275 slabs were respectively used to construct the training, validation and test sets.…”

“…The most related algorithm to our work was proposed by [53], and it used an approach of semantic segmentation [54] for recognizing machine-printed SINs in factory scenes. In [53], semantic region of each character was defined as a rectangular region to generate GTD, and individual characters were recognized by using characteristics of machine-printed characters such as consistent aspect ratios and similar distances between characters. However, this algorithm is not applicable to recognize handwritten SINs due to irregular spacing between handwritten characters and various aspect ratios.…”

End-to-end Billet Identification Number Recognition System

“…Recently, deep learning algorithms, which do not have this drawback, have outperformed other methods in the steel product number recognition. 16) In previous studies, 17) the fully convolutional network 18) (FCN) was employed in slab identification number recognition. In ther present study, a novel BIN recognition system is proposed based on these studies.…”

Optimal Charge Planning Model of Steelmaking Based on Multi-Objective Evolutionary Algorithm

“…As having an important role in manufacturing industries, the iron and steel industry also proceeds in some explorations of intelligent manufacturing from the perspective of equipment technique to planning and scheduling in order to keep competitiveness in metallurgical industry [5][6][7][8]. In addition, with the increasingly fierce market competition and the current serious overcapacity of domestic steel production, the contract orders of steel products present a trend of multi-variety, small-batch, as well as short due date.…”