| The applications presented utilized tools that are | | | | Generally, the training required for using such |
| developed from image processing algorithms. In | | | | systems is minimal since most software packages |
| the inspection of correctly inserted print | | | | supplied by vision systems manufacturers are |
| templates.it has been shown for instance that two | | | | user-friendly. The inspection for quality also |
| feature detection algorithms can be applied; in this | | | | requires very simple tools like those that have |
| case canned in the software described as feature | | | | been demonstrated such as feature count and |
| detection tools. If the print template is inverted in | | | | template matching. |
| any way, whether upside down or left to right, | | | | After the molding process is over, the part is |
| either or both tools will return a "fail" based on the | | | | removed from the mold cavity manually, and |
| prescribed dark or bright feature size required | | | | visually inspected for quality. Despite this, process |
| across the tools. For print quality, two methods | | | | variations could cause minor blemishes or smears |
| have been described. The first is to use a | | | | on the print that are not immediately visible to |
| template match of a good print and compare it | | | | the operator. Figure S shows an example of such |
| with other parts. This was mainly used to detect | | | | a defect with a close-up on a print revealing a |
| smudges, smears and poorly printed characters. | | | | small smear on the letter "d." Two methods can |
| Provided the degree of mismatch is adequately | | | | be used for this inspection.The first is to use a |
| defined, the template match can be used fairly | | | | temporal operation such as the template match |
| adequately. In this particular case study, the | | | | described in section 2.S.The training data is |
| template match could not be tested extensively | | | | obtained from a captured image of what is |
| because of lack of adequate samples.The second | | | | perceived as a very good quality print. |
| method used algorithms for reading optical | | | | Subsequent images can then be captured from |
| characters (OCR).The printed characters on a | | | | parts as they flow along a conveyor, and each |
| good plastic part, which are not standard OCR | | | | image compared with the trained data. A problem |
| fonts, were read into an OCR tool.Through | | | | such as a smear or a missing character may |
| software, the tool was trained to recognize these | | | | cause a mismatch in the number and position of |
| as OCR fonts with varying degrees of | | | | dark pixels that are in the image. Figure 6 is an |
| acceptance. Like in the case of the template | | | | illustration of the application of this tool. |
| match, the OCR was not tested extensively due | | | | Another useful tool that would he used to inspect |
| to lack of adequate different production | | | | a print is an optical character reader (OCR). |
| samples.For example casting mould,mold | | | | Although the prints are not true optical |
| making,plastic injection mold etc. | | | | characters, using the software, normal non-OCR |
| A variety of such software and hardware exist in | | | | font characters can be trained to correspond to a |
| the market today. The comparison between the | | | | particular print image.After an image of a good |
| different software/hardware platforms is not | | | | print is captured, using this software, the actual |
| intended to be the subject of this paper; however | | | | character string is typed into the OCR reader. |
| a comprehensive listing can be obtained from the | | | | The reader is then "trained" to interpret the |
| Automated Imaging Association.20 Plastic molding | | | | image data as corresponding to character string |
| processes are widely used in the manufacturing | | | | from the keyboard entry. After several trials, an |
| of various engineering and consumer items. The | | | | acceptance level for allowing the captured image |
| growth of the plastics sector has seen a slight | | | | characters as ones that match the corresponding |
| decline (-5% overall) in the U.S. since 2000 due to | | | | keyboard characters is determined. If any of the |
| the increasing costs of fuel and gas, the | | | | characters from a subsequent part contains a |
| weakening of the dollar against major currencies | | | | large smear it would not match the trained data |
| in the world, and more so, the movement of | | | | set. Additionally, if there is a missing character on |
| manufacturing to Asia (especially China). This | | | | a plastic part, the string will not match the trained |
| deficit has been absorbed mainly by China, Canada | | | | one. An example of this is shown in Figure . There |
| and Japan. Despite this, there is still a substantial | | | | are two limitations with this tool however. The |
| proportion of manufacturing companies in the U.S., | | | | first is that there ought to he adequate spacing |
| especially in the molding industry. Thus there is still | | | | hetween the characters for it to work effectively. |
| a great need for improved process and quality | | | | secondly, minor smears on the prints may not |
| control. This paper presents a simple approach | | | | easily he detected. Such limitations have heen |
| that utilizes commercially available hardware and | | | | addressed hy the use of advanced processing |
| software for machine vision applications to | | | | algorithms such as those that utilize neural-fuzzy |
| automate the inspection of molded plastics. | | | | classifiers. |