CDIA Image Capture & Processing Techniques 5 — Questions and Answers
Question 1: In document capture, what does 'throughput' measure for a production scanner?
- The optical resolution in dots per inch
- The number of pages processed per minute (ppm) or images per minute (ipm) (Correct answer)
- The file size of each scanned image
- The number of OCR zones recognized per document
Correct answer: The number of pages processed per minute (ppm) or images per minute (ipm)
Scanner throughput, measured in pages per minute (ppm) or images per minute (ipm), indicates how many document sides can be digitized in a given time period.
Question 2: Which process detects and marks blank pages during scanning so they can be automatically excluded from the document set?
- Auto-crop
- Blank page detection (Correct answer)
- Patch code recognition
- Background removal
Correct answer: Blank page detection
Blank page detection analyzes pixel content density and removes pages that fall below a defined threshold of ink coverage, preventing empty pages from entering the document repository.
Question 3: What challenge does scanning mixed-size document batches (e.g., letter and legal pages together) present?
- The scanner cannot detect color on different page sizes
- The automatic document feeder may misfeed, and image cropping must dynamically adjust to each page's dimensions (Correct answer)
- OCR cannot process different page sizes in one batch
- Compression algorithms differ by page size and cannot be mixed
Correct answer: The automatic document feeder may misfeed, and image cropping must dynamically adjust to each page's dimensions
Mixed-size batches risk mechanical misfeeds in the ADF and require auto-size detection so the scanner crops each image to the actual document dimensions rather than a fixed template.
Question 4: What is the effect of increasing JPEG compression quality on a scanned document image?
- Larger file size with better image fidelity and fewer compression artifacts (Correct answer)
- Smaller file size with better image fidelity
- Larger file size with more compression artifacts
- No change in file size, only image color accuracy changes
Correct answer: Larger file size with better image fidelity and fewer compression artifacts
Higher JPEG quality settings reduce compression ratios, retaining more image data and reducing artifacts such as blocking, but producing proportionally larger output files.
Question 5: Which technique allows a scanner to automatically detect the document boundaries and remove the excess scanner bed background from the image?
- Deskew
- Auto-crop (content detection) (Correct answer)
- Descreen
- Noise reduction
Correct answer: Auto-crop (content detection)
Auto-crop or content detection algorithms identify the actual document edges by detecting contrast differences between the paper and the scanner background, trimming the image to the document boundary.
Question 6: In document imaging, what is 'intelligent character recognition' (ICR) designed to handle that standard OCR cannot?
- Printed machine fonts in multiple languages
- Handwritten text and cursive script (Correct answer)
- Barcodes and QR codes on documents
- Embedded images within scanned documents
Correct answer: Handwritten text and cursive script
ICR extends OCR capabilities by using pattern recognition and machine learning to interpret handwritten characters and cursive writing, which standard OCR engines typically cannot process accurately.
Question 7: What is the significance of the AIIM/ISO standards for document scanning in enterprise capture systems?
- They mandate specific hardware vendors for document capture
- They define quality benchmarks, metadata standards, and best practices ensuring interoperability and archival integrity (Correct answer)
- They limit document scanning to specific file formats only
- They require all scanned documents to be stored in cloud systems
Correct answer: They define quality benchmarks, metadata standards, and best practices ensuring interoperability and archival integrity
AIIM and ISO standards (such as ISO 19005 for PDF/A) establish guidelines for scan quality, metadata, file formats, and processes that ensure long-term accessibility, legal admissibility, and system interoperability.
CDIA Image Capture & Processing Techniques 5
In document capture, what does 'throughput' measure for a production scanner?