| Character | Data about detected character. |
| CharacterRecognitionResult | Pages with detected characters data. |
| ContentArea | A content area detected in an image. |
| DefectAreas | Image areas containing a certain type of defect. |
| LanguageDetectionOutput | Languages detected in the image text. |
| LayoutOutput | Information on detected content areas in the image. |
| OCRTable | Represents one table with recognized tabular data. |
| OCRTableCell | Represents one table cell with recognized text and position information. |
| OCRTablePage | Represents structured table data for the entire OCR document’s page. |
| OCRTableRow | Represents a single row within a recognized table. |
| OnnxRuntimeSessionOptions | Configuration options for creating ONNX InferenceSession. |
| SkewOutput | Data about skew angle in degrees and name of the file. |